##Opening database

library(readxl)
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)

# Load the necessary packages
library(knitr)  # For formatted table printing
library(epitools)  # For odds ratio and confidence interval calculations

# Install and load the knitr package if not already installed
install.packages("knitr")
# Install the 'epitools' package if not already installed
install.packages("epitools")

################################################ Univariate analysis #############################################################
############################################### Comparisons by Gender (Woman vs men) #############################################
---------------------------------------------------------------------------------------------------------------
  
  ##CUSIN1 (I wash my hands before cooking (No= 9.4%))
  
  # Ensure that the dataframe name is consistent
  df_filtered <- Database_simplified[Database_simplified$CUSIN1 %in% c(0, 1) & Database_simplified$GENRE %in% c(0, 1), ]
# Create the contingency table
table <- table(df_filtered$CUSIN1, df_filtered$GENRE)
# Add descriptive labels to rows and columns
rownames(table) <- c("CUSIN1 (Yes)", "CUSIN1 (No)")
colnames(table) <- c("Female Gender", "Male Gender")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Gender vs. Hand Washing")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

-------------------------------------------------------------------------------------------------------
  
  ##CUSIN2 (After handling raw food (meat and vegetables), I wash my hands with soap (No= 15.1%)
  
  # Ensure that the dataframe name is consistent
  df_filtered <- Database_simplified[Database_simplified$CUSIN2 %in% c(0, 1) & Database_simplified$GENRE %in% c(0, 1), ]
# Create the contingency table
table <- table(df_filtered$CUSIN2, df_filtered$GENRE)
# Add descriptive labels to rows and columns
rownames(table) <- c("CUSIN2 (Yes)", "CUSIN2 (No)")
colnames(table) <- c("Female Gender", "Male Gender")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Gender vs. After handling raw food (meat and vegetables), I wash my hands with soap")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN3 (I use the same kitchen utensils for handling raw and ready-to-eat foods (Yes=25.8%))
  
  # Ensure that the dataframe name is consistent
  df_filtered <- Database_simplified[Database_simplified$CUSIN3 %in% c(0, 1) & Database_simplified$GENRE %in% c(0, 1), ]
# Create the contingency table
table <- table(df_filtered$CUSIN3, df_filtered$GENRE)
# Add descriptive labels to rows and columns
rownames(table) <- c("CUSIN3 (Yes)", "CUSIN3 (No)")
colnames(table) <- c("Female Gender", "Male Gender")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Gender vs. I use the same kitchen utensils for handling raw and ready-to-eat foods")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

-------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN4 (I wash kitchen utensils that have been used for raw food before using them to prepare other foods  (No=16.8%))
  
  # Ensure that the dataframe name is consistent
  df_filtered <- Database_simplified[Database_simplified$CUSIN4 %in% c(0, 1) & Database_simplified$GENRE %in% c(0, 1), ]
# Create the contingency table
table <- table(df_filtered$CUSIN4, df_filtered$GENRE)
# Add descriptive labels to rows and columns
rownames(table) <- c("CUSIN4 (Yes)", "CUSIN4 (No)")
colnames(table) <- c("Female Gender", "Male Gender")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Gender vs. I wash kitchen utensils that have been used for raw food before using them to prepare other foods")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

-------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN5 (I wash fruits and vegetables before eating them (No=20.7%))
  
  # Ensure that the dataframe name is consistent
  df_filtered <- Database_simplified[Database_simplified$CUSIN5 %in% c(0, 1) & Database_simplified$GENRE %in% c(0, 1), ]
# Create the contingency table
table <- table(df_filtered$CUSIN5, df_filtered$GENRE)
# Add descriptive labels to rows and columns
rownames(table) <- c("CUSIN5 (Yes)", "CUSIN5 (No)")
colnames(table) <- c("Female Gender", "Male Gender")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Gender vs. I wash fruits and vegetables before eating them")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

-------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN6 (I wash my hands before eating (No=21.5))
  
  # Ensure that the dataframe name is consistent
  df_filtered <- Database_simplified[Database_simplified$CUSIN6 %in% c(0, 1) & Database_simplified$GENRE %in% c(0, 1), ]
# Create the contingency table
table <- table(df_filtered$CUSIN6, df_filtered$GENRE)
# Add descriptive labels to rows and columns
rownames(table) <- c("CUSIN6 (Yes)", "CUSIN6 (No)")
colnames(table) <- c("Female Gender", "Male Gender")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Gender vs. I wash my hands before eating")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

---------------------------------------------------------------------------------------------------------------------
  
  ##PRESCATB1 When you get a prescription for antibiotics, do you follow the recommended 
  ##length of treatment and daily dosage? (No=4.2%) (Sometimes=9.6%) (No+Sometimes=13.8%)
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)

############### 1st scenario= No
# Make sure 'Database_simplified' is the correct name of your dataframe
df <- Database_simplified
# Filter only 'Yes' and 'No' responses for PRESCATB1 and genders 'Female' and 'Male'
df_filtered_prescatb1 <- df[df$PRESCATB1 %in% c(0, 1) & df$GENRE %in% c(0, 1), ]
# Create the contingency table
table_prescatb1 <- table(df_filtered_prescatb1$PRESCATB1, df_filtered_prescatb1$GENRE)
# Add descriptive labels to the rows and columns
rownames(table_prescatb1) <- c("Yes", "No")
colnames(table_prescatb1) <- c("Female", "Male")
# Perform the Chi-Squared test
chi_result_prescatb1 <- chisq.test(table_prescatb1)
# Calculate the odds ratio and confidence interval
odds_ratio_prescatb1 <- oddsratio(table_prescatb1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_prescatb1, caption = "Contingency Table: Gender vs. Following Prescription for Antibiotics"))
# Print the results of the Chi-Squared test
print(chi_result_prescatb1)
# Print the odds ratio and confidence interval
print(odds_ratio_prescatb1)

################## 2nd scenario= Sometimes
# Filter for 'Yes' and 'Sometimes' responses for PRESCATB1 and genders 'Female' and 'Male'
df_filtered_prescatb1_sometimes <- df[df$PRESCATB1 %in% c(0, 3) & df$GENRE %in% c(0, 1), ]
# Create the contingency table for 'Yes' vs 'Sometimes'
table_prescatb1_sometimes <- table(df_filtered_prescatb1_sometimes$PRESCATB1, df_filtered_prescatb1_sometimes$GENRE)
# Adjust the table to have 'Yes' and 'Sometimes' as row names
# This step assumes that both 'Yes' and 'Sometimes' responses are present in the filtered data
if (all(c(0, 3) %in% df_filtered_prescatb1_sometimes$PRESCATB1)) {
  rownames(table_prescatb1_sometimes) <- c("Yes", "Sometimes")
} else {
  stop("Not all expected PRESCATB1 responses (Yes and Sometimes) are present in the filtered data.")
}
# Perform the Chi-Squared test
chi_result_prescatb1_sometimes <- chisq.test(table_prescatb1_sometimes)
# Calculate the odds ratio and confidence interval
odds_ratio_prescatb1_sometimes <- oddsratio(table_prescatb1_sometimes, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_prescatb1_sometimes, caption = "Contingency Table: Gender vs. Following Prescription for Antibiotics Sometimes"))
# Print the results of the Chi-Squared test
print(chi_result_prescatb1_sometimes)
# Print the odds ratio and confidence interval
print(odds_ratio_prescatb1_sometimes)

################## 3rd scenario= No+Sometimes
# Filter for 'Yes', 'No', and 'Sometimes' responses for PRESCATB1 and genders 'Female' and 'Male'
df_filtered_prescatb1_combined <- df[df$PRESCATB1 %in% c(0, 1, 3) & df$GENRE %in% c(0, 1), ]
# Create a new variable for the combined 'No' and 'Sometimes' condition
df_filtered_prescatb1_combined$No_Sometimes <- df_filtered_prescatb1_combined$PRESCATB1 %in% c(1, 3)
# Create the contingency table for 'Yes' vs 'No+Sometimes'
table_prescatb1_combined <- table(df_filtered_prescatb1_combined$No_Sometimes, df_filtered_prescatb1_combined$GENRE)
# Adjust the table to have 'Yes' and 'No+Sometimes' as row names
rownames(table_prescatb1_combined) <- c("Yes", "No_Sometimes")
# Perform the Chi-Squared test
chi_result_prescatb1_combined <- chisq.test(table_prescatb1_combined)
# Calculate the odds ratio and confidence interval
odds_ratio_prescatb1_combined <- oddsratio(table_prescatb1_combined, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_prescatb1_combined, caption = "Contingency Table: Gender vs. Following Prescription for Antibiotics (Yes vs. No+Sometimes)"))
# Print the results of the Chi-Squared test
print(chi_result_prescatb1_combined)
# Print the odds ratio and confidence interval
print(odds_ratio_prescatb1_combined)

---------------------------------------------------------------------------------------------------------------------
  
  ##ARRETATB Do you stop taking antibiotics when symptoms start to disappear?
  ##(Always=7.3%) (Sometimes=20.4%) (Always+Sometimes=27.7%)
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)

############### 1st scenario= Always
# Filter for 'Always' and 'Never' responses for ARRETATB and genders 'Female' and 'Male'
df_filtered_arretatb <- df[df$ARRETATB %in% c(0, 1) & df$GENRE %in% c(0, 1), ]
# Create the contingency table for 'Always' vs 'Never'
table_arretatb <- table(df_filtered_arretatb$ARRETATB, df_filtered_arretatb$GENRE)
# Add descriptive labels to the rows and columns
rownames(table_arretatb) <- c("Always", "Never")
colnames(table_arretatb) <- c("Female", "Male")
# Perform the Chi-Squared test
chi_result_arretatb <- chisq.test(table_arretatb)
# Calculate the odds ratio and confidence interval
odds_ratio_arretatb <- oddsratio(table_arretatb, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_arretatb, caption = "Contingency Table: Gender vs. Stopping Antibiotics Always vs. Never"))
# Print the results of the Chi-Squared test
print(chi_result_arretatb)
# Print the odds ratio and confidence interval
print(odds_ratio_arretatb)

################# 2nd Cenario: Sometimes
# Filter for 'Sometimes' and 'Never' responses for ARRETATB and genders 'Female' and 'Male'
df_filtered_arretatb_sometimes <- df[df$ARRETATB %in% c(1, 2) & df$GENRE %in% c(0, 1), ]
# Create the contingency table for 'Sometimes' vs 'Never'
table_arretatb_sometimes <- table(df_filtered_arretatb_sometimes$ARRETATB == 2, df_filtered_arretatb_sometimes$GENRE)
# Add descriptive labels to the rows and columns
rownames(table_arretatb_sometimes) <- c("Never", "Sometimes")
colnames(table_arretatb_sometimes) <- c("Female", "Male")
# Perform the Chi-Squared test
chi_result_arretatb_sometimes <- chisq.test(table_arretatb_sometimes)
# Calculate the odds ratio and confidence interval
odds_ratio_arretatb_sometimes <- oddsratio(table_arretatb_sometimes, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_arretatb_sometimes, caption = "Contingency Table: Gender vs. Stopping Antibiotics Sometimes vs. Never"))
# Print the results of the Chi-Squared test
print(chi_result_arretatb_sometimes)
# Print the odds ratio and confidence interval
print(odds_ratio_arretatb_sometimes)

############### #3rd scenario= Sometimes+Always
# Filter for 'Always', 'Never', and 'Sometimes' responses for ARRETATB and genders 'Female' and 'Male'
df_filtered_arretatb_combined <- df[df$ARRETATB %in% c(0, 1, 2) & df$GENRE %in% c(0, 1), ]
# Create a new variable for the combined 'Sometimes' and 'Always' condition
df_filtered_arretatb_combined$Sometimes_Always <- df_filtered_arretatb_combined$ARRETATB %in% c(0, 2)
# Create the contingency table for 'Sometimes+Always' vs 'Never'
table_arretatb_combined <- table(df_filtered_arretatb_combined$Sometimes_Always, df_filtered_arretatb_combined$GENRE)
# Add descriptive labels to the rows and columns
rownames(table_arretatb_combined) <- c("Never", "Sometimes_Always")
colnames(table_arretatb_combined) <- c("Female", "Male")
# Perform the Chi-Squared test
chi_result_arretatb_combined <- chisq.test(table_arretatb_combined)
# Calculate the odds ratio and confidence interval
odds_ratio_arretatb_combined <- oddsratio(table_arretatb_combined, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_arretatb_combined, caption = "Contingency Table: Gender vs. Stopping Antibiotics (Sometimes+Always vs. Never)"))
# Print the results of the Chi-Squared test
print(chi_result_arretatb_combined)
# Print the odds ratio and confidence interval
print(odds_ratio_arretatb_combined)

---------------------------------------------------------------------------------------------------------------------
  
  ##ATBORAL1 Have you ever taken an oral antibiotic treatment (by mouth) without a medical prescription? (Yes=12.3%)
  
  # Make sure 'Database_simplified' is the correct name of your dataframe
  df <- Database_simplified
# Filter for 'Yes' and 'No' responses for ATBORAL and genders 'Female' and 'Male'
df_filtered_atboral <- df[df$ATBORAL1 %in% c(0, 1) & df$GENRE %in% c(0, 1), ]
# Create the contingency table for 'Yes' vs 'No'
table_atboral <- table(df_filtered_atboral$ATBORAL1, df_filtered_atboral$GENRE)
# Add descriptive labels to the rows and columns
rownames(table_atboral) <- c("Yes", "No")
colnames(table_atboral) <- c("Female", "Male")
# Perform the Chi-Squared test
chi_result_atboral <- chisq.test(table_atboral)
# Calculate the odds ratio and confidence interval
odds_ratio_atboral <- oddsratio(table_atboral, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atboral, caption = "Contingency Table: Gender vs. Taking Oral Antibiotics Without Prescription (Yes vs. No)"))
# Print the results of the Chi-Squared test
print(chi_result_atboral)
# Print the odds ratio and confidence interval
print(odds_ratio_atboral)

--------------------------------------------------------------------------------------------------------
  
  ### ATBANI1 I can exchange resistant bacteria with my pet (False=23.2%)
  
  # Make sure 'Database_simplified' is the correct name of your dataframe
  df <- Database_simplified
# Filter for 'True' and 'False' responses for ATBANI1 and genders 'Female' and 'Male'
df_filtered_atbani1 <- df[df$ATBANI1 %in% c(0, 1) & df$GENRE %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_atbani1 <- table(df_filtered_atbani1$ATBANI1, df_filtered_atbani1$GENRE)
# Add descriptive labels to the rows and columns
rownames(table_atbani1) <- c("True", "False")
colnames(table_atbani1) <- c("Female", "Male")
# Perform the Chi-Squared test
chi_result_atbani1 <- chisq.test(table_atbani1)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani1 <- oddsratio(table_atbani1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani1, caption = "Contingency Table: Gender vs. Exchanging Resistant Bacteria with Pets (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani1)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani1)

---------------------------------------------------------------------------------------------------------------------
  
  ### ATBANI2=The use of antibiotics in livestock and crops can increase the 
  #presence of resistant bacteria in the environment (False=14.7%)
  
  # Ensure 'Database_simplified' is the correct name of your dataframe
  df <- Database_simplified
# Filter for 'True' and 'False' responses for ATBANI2 and genders 'Female' and 'Male'
df_filtered_atbani2 <- df[df$ATBANI2 %in% c(0, 1) & df$GENRE %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_atbani2 <- table(df_filtered_atbani2$ATBANI2, df_filtered_atbani2$GENRE)
# Add descriptive labels to the rows and columns
rownames(table_atbani2) <- c("True", "False")
colnames(table_atbani2) <- c("Female", "Male")
# Perform the Chi-Squared test
chi_result_atbani2 <- chisq.test(table_atbani2)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani2 <- oddsratio(table_atbani2, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani2, caption = "Contingency Table: Gender vs. Antibiotics in Livestock and Crops Affecting Environment (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani2)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani2)


--------------------------------------------------------------------------------------------------------------------
  
  ##### ATBANI3	The use of antibiotics in livestock and crops can affect me directly
  ##(I can get resistant bacteria in my body) (False=26.3%)
  
  # Ensure 'Database_simplified' is the correct name of your dataframe
  df <- Database_simplified
# Filter for 'True' and 'False' responses for ATBANI3 and genders 'Female' and 'Male'
df_filtered_atbani3 <- df[df$ATBANI3 %in% c(0, 1) & df$GENRE %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_atbani3 <- table(df_filtered_atbani3$ATBANI3, df_filtered_atbani3$GENRE)
# Add descriptive labels to the rows and columns
rownames(table_atbani3) <- c("True", "False")
colnames(table_atbani3) <- c("Female", "Male")
# Perform the Chi-Squared test
chi_result_atbani3 <- chisq.test(table_atbani3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani3 <- oddsratio(table_atbani3, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani3, caption = "Contingency Table: Gender vs. Antibiotics in Livestock and Crops Affecting Humans Directly (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani3)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani3)

-------------------------------------------------------------------------------------------------------------------
  ##### ATBANI4	Resistant bacteria are only found in hospitals (True=10.8%)
  
  # Ensure 'Database_simplified' is the correct name of your dataframe
  df <- Database_simplified
# Filter for 'True' and 'False' responses for ATBANI4 and genders 'Female' and 'Male'
df_filtered_atbani4 <- df[df$ATBANI4 %in% c(0, 1) & df$GENRE %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_atbani4 <- table(df_filtered_atbani4$ATBANI4, df_filtered_atbani4$GENRE)
# Add descriptive labels to the rows and columns
rownames(table_atbani4) <- c("True", "False")
colnames(table_atbani4) <- c("Female", "Male")
# Perform the Chi-Squared test
chi_result_atbani4 <- chisq.test(table_atbani4)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani4 <- oddsratio(table_atbani4, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani4, caption = "Contingency Table: Gender vs. Resistant Bacteria Found Only in Hospitals (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani4)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani4)

----------------------------------------------------------------------------------------------------------------------
  
  #####RESATB1	Antibiotic resistance occurs when your body becomes resistant to antibiotics and they
  ##no longer work as well (True=58.3%)
  
  # Load the database
  df <- Database_simplified
# Filter for 'True' and 'False' responses for RESATB1 and genders 'Female' and 'Male'
df_filtered_resatb1 <- df[df$RESATB1 %in% c(0, 1) & df$GENRE %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_resatb1 <- table(df_filtered_resatb1$RESATB1, df_filtered_resatb1$GENRE)
# Add descriptive labels to rows and columns
rownames(table_resatb1) <- c("True", "False")
colnames(table_resatb1) <- c("Female", "Male")
# Perform the Chi-Squared test
chi_result_resatb1 <- chisq.test(table_resatb1)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb1 <- oddsratio(table_resatb1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb1, caption = "Contingency Table: Gender vs. Understanding of Antibiotic Resistance (RESATB1: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb1)
print(odds_ratio_resatb1)

-------------------------------------------------------------------------------------------------------------------
  
  #####RESATB2	Many infections are becoming increasingly resistant to antibiotic treatment  (False=12.5%)
  
  # Load the database
  df <- Database_simplified
# Filter for 'True' and 'False' responses for RESATB2 and genders 'Female' and 'Male'
df_filtered_resatb2 <- df[df$RESATB2 %in% c(0, 1) & df$GENRE %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_resatb2 <- table(df_filtered_resatb2$RESATB2, df_filtered_resatb2$GENRE)
# Add descriptive labels to rows and columns
rownames(table_resatb2) <- c("True", "False")
colnames(table_resatb2) <- c("Female", "Male")
# Perform the Chi-Squared test
chi_result_resatb2 <- chisq.test(table_resatb2)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb2 <- oddsratio(table_resatb2, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb2, caption = "Contingency Table: Gender vs. Perception of Increasing Infection Resistance (RESATB2: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb2)
print(odds_ratio_resatb2)

---------------------------------------------------------------------------------------------------------------------
  #####RESATB3	If bacteria are resistant to antibiotics, it can be very difficult or impossible to treat the infections they cause (False=16.7%)
  
  # Load the database
  df <- Database_simplified
# Filter for 'True' and 'False' responses for RESATB3 and genders 'Female' and 'Male'
df_filtered_resatb3 <- df[df$RESATB3 %in% c(0, 1) & df$GENRE %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_resatb3 <- table(df_filtered_resatb3$RESATB3, df_filtered_resatb3$GENRE)
# Add descriptive labels to rows and columns
rownames(table_resatb3) <- c("True", "False")
colnames(table_resatb3) <- c("Female", "Male")
# Perform the Chi-Squared test
chi_result_resatb3 <- chisq.test(table_resatb3)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb3 <- oddsratio(table_resatb3, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb3, caption = "Contingency Table: Gender vs. Perception of Difficulty Treating Infections (RESATB3: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb3)
print(odds_ratio_resatb3)
----------------------------------------------------------------------------------------------------------------------
  #####RESATB4	Antibiotic resistance is an issue that could affect me or my family (False=11.8%)
  
  # Load the database
  df <- Database_simplified
# Filter for 'True' and 'False' responses for RESATB4 and genders 'Female' and 'Male'
df_filtered_resatb4 <- df[df$RESATB4 %in% c(0, 1) & df$GENRE %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_resatb4 <- table(df_filtered_resatb4$RESATB4, df_filtered_resatb4$GENRE)
# Add descriptive labels to rows and columns
rownames(table_resatb4) <- c("True", "False")
colnames(table_resatb4) <- c("Female", "Male")
# Perform the Chi-Squared test
chi_result_resatb4 <- chisq.test(table_resatb4)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb4 <- oddsratio(table_resatb4, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb4, caption = "Contingency Table: Gender vs. Perception of Antibiotic Resistance Affecting One's Family (RESATB4: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb4)
print(odds_ratio_resatb4)

---------------------------------------------------------------------------------------------------------------------
  #####RESATB5	Antibiotic resistance is an issue in other countries but not here (True=9.9%)
  
  # Load the database
  df <- Database_simplified
# Filter for 'True' and 'False' responses for RESATB5 and genders 'Female' and 'Male'
df_filtered_resatb5 <- df[df$RESATB5 %in% c(0, 1) & df$GENRE %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_resatb5 <- table(df_filtered_resatb5$RESATB5, df_filtered_resatb5$GENRE)
# Add descriptive labels to rows and columns
rownames(table_resatb5) <- c("True", "False")
colnames(table_resatb5) <- c("Female", "Male")
# Perform the Chi-Squared test
chi_result_resatb5 <- chisq.test(table_resatb5)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb5 <- oddsratio(table_resatb5, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb5, caption = "Contingency Table: Gender vs. Perception of Antibiotic Resistance as an Issue Only in Other Countries (RESATB5: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb5)
print(odds_ratio_resatb5)
---------------------------------------------------------------------------------------------------------------------  
  
  #####RESATB6	Antibiotic resistance is only a problem for people who take antibiotics regularly (True=17.5%)
  
  # Load the database
  df <- Database_simplified
# Filter for 'True' and 'False' responses for RESATB6 and genders 'Female' and 'Male'
df_filtered_resatb6 <- df[df$RESATB6 %in% c(0, 1) & df$GENRE %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_resatb6 <- table(df_filtered_resatb6$RESATB6, df_filtered_resatb6$GENRE)
# Add descriptive labels to rows and columns
rownames(table_resatb6) <- c("True", "False")
colnames(table_resatb6) <- c("Female", "Male")
# Perform the Chi-Squared test
chi_result_resatb6 <- chisq.test(table_resatb6)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb6 <- oddsratio(table_resatb6, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb6, caption = "Contingency Table: Gender vs. Perception of Antibiotic Resistance as a Problem Only for Regular Antibiotic Users (RESATB6: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb6)
print(odds_ratio_resatb6)

--------------------------------------------------------------------------------------------------------------------- 
  #####RESATB7	Bacteria that are resistant to antibiotics can be spread from person to person (False=20.2%)
  
  # Load the database
  df <- Database_simplified
# Filter for 'True' and 'False' responses for RESATB7 and genders 'Female' and 'Male'
df_filtered_resatb7 <- df[df$RESATB7 %in% c(0, 1) & df$GENRE %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_resatb7 <- table(df_filtered_resatb7$RESATB7, df_filtered_resatb7$GENRE)
# Add descriptive labels to rows and columns
rownames(table_resatb7) <- c("True", "False")
colnames(table_resatb7) <- c("Female", "Male")
# Perform the Chi-Squared test
chi_result_resatb7 <- chisq.test(table_resatb7)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb7 <- oddsratio(table_resatb7, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb7, caption = "Contingency Table: Gender vs. Perception of Bacteria Transmission Person to Person (RESATB7: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb7)
print(odds_ratio_resatb7)

--------------------------------------------------------------------------------------------------------------------
  #####RESATB8	Antibiotic-resistant infections could make medical procedures like surgery, organ transplants,
  ##and cancer treatment much more dangerous (False=12.0%)
  
  # Load the database
  df <- Database_simplified
# Filter for 'True' and 'False' responses for RESATB8 and genders 'Female' and 'Male'
df_filtered_resatb8 <- df[df$RESATB8 %in% c(0, 1) & df$GENRE %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_resatb8 <- table(df_filtered_resatb8$RESATB8, df_filtered_resatb8$GENRE)
# Add descriptive labels to rows and columns
rownames(table_resatb8) <- c("True", "False")
colnames(table_resatb8) <- c("Female", "Male")
# Perform the Chi-Squared test
chi_result_resatb8 <- chisq.test(table_resatb8)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb8 <- oddsratio(table_resatb8, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb8, caption = "Contingency Table: Gender vs. Perception of Antibiotic-Resistant Infections and Medical Procedures (RESATB8: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb8)
print(odds_ratio_resatb8)

--------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL1	Farmers should give fewer antibiotics to food-producing animals 
  
  ##################### 1st scenario (Strongly desagree=8.68%) vs. Strongly Agree
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
# Load dataframe
df <- Database_simplified
# Filter for 'Strongly Agree' (3) and 'Strongly Disagree' (1) responses for ATBRGL1 and genders 'Female' (0) and 'Male' (1)
df_filtered_atbrgl1_scenario1 <- df[df$ATBRGL1 %in% c(1, 3) & df$GENRE %in% c(0, 1), ]
# Create the contingency table for 'Strongly Agree' vs 'Strongly Disagree'
table_atbrgl1_scenario1 <- table(df_filtered_atbrgl1_scenario1$ATBRGL1, df_filtered_atbrgl1_scenario1$GENRE)
# Add descriptive labels to rows and columns
rownames(table_atbrgl1_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl1_scenario1) <- c("Female", "Male")
# Perform the Chi-Squared test
chi_result_atbrgl1_scenario1 <- chisq.test(table_atbrgl1_scenario1)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl1_scenario1 <- oddsratio(table_atbrgl1_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl1_scenario1, caption = "Contingency Table: Gender vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_atbrgl1_scenario1)
print(odds_ratio_atbrgl1_scenario1)

############################# 2nd scenario Farmers should give fewer antibiotics to
##food-producing animals (Neither agree nor desagree=22.6%) vs. Strongly Agree
# Load dataframe
df <- Database_simplified
# Filter for 'Strongly Agree' (3) and 'Neither Agree Nor Disagree' (2) responses for ATBRGL1 and genders 'Female' (0) and 'Male' (1)
df_filtered_atbrgl1_scenario2 <- df[df$ATBRGL1 %in% c(2, 3) & df$GENRE %in% c(0, 1), ]
# Create the contingency table for 'Strongly Agree' vs 'Neither Agree Nor Disagree'
table_atbrgl1_scenario2 <- table(df_filtered_atbrgl1_scenario2$ATBRGL1, df_filtered_atbrgl1_scenario2$GENRE)
# Add descriptive labels to rows and columns
rownames(table_atbrgl1_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl1_scenario2) <- c("Female", "Male")
# Perform the Chi-Squared test
chi_result_atbrgl1_scenario2 <- chisq.test(table_atbrgl1_scenario2)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl1_scenario2 <- oddsratio(table_atbrgl1_scenario2, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl1_scenario2, caption = "Contingency Table: Gender vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Neither Agree Nor Disagree)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_atbrgl1_scenario2)
print(odds_ratio_atbrgl1_scenario2)

############################# 3rd scenario (Strongly desagree + Neither agree nor desagree=31.28%) vs. Strongly Agree
# Load dataframe
df <- Database_simplified
# Filter for 'Strongly Agree' (3), 'Strongly Disagree' (1) and 'Neither Agree Nor Disagree' (2) responses for ATBRGL1 and genders 'Female' (0) and 'Male' (1)
df_filtered_atbrgl1_scenario3 <- df[df$ATBRGL1 %in% c(1, 2, 3) & df$GENRE %in% c(0, 1), ]
# Create a new variable for the combined 'Strongly Disagree' and 'Neither Agree Nor Disagree' condition
df_filtered_atbrgl1_scenario3$Disagree_Neither <- df_filtered_atbrgl1_scenario3$ATBRGL1 %in% c(1, 2)
# Create the contingency table for 'Strongly Agree' vs 'Strongly Disagree + Neither Agree Nor Disagree'
table_atbrgl1_scenario3 <- table(df_filtered_atbrgl1_scenario3$Disagree_Neither, df_filtered_atbrgl1_scenario3$GENRE)
# Add descriptive labels to rows and columns
rownames(table_atbrgl1_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl1_scenario3) <- c("Female", "Male")
# Perform the Chi-Squared test
chi_result_atbrgl1_scenario3 <- chisq.test(table_atbrgl1_scenario3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl1_scenario3 <- oddsratio(table_atbrgl1_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl1_scenario3, caption = "Contingency Table: Gender vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree + Neither)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_atbrgl1_scenario3)
print(odds_ratio_atbrgl1_scenario3)

--------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL2	People should not keep antibiotics and use them later for other illnesses  
  
  ############################# 1st scenario Strongly desagree vs. Strongly Agree
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
# Load the database
df <- Database_simplified
## Scenario 1: Strongly Disagree vs. Strongly Agree
# Filter for 'Strongly Agree' (3) and 'Strongly Disagree' (1) responses for ATBRGL2 and genders 'Female' (0) and 'Male' (1)
df_filtered_atbrgl2_scenario1 <- df[df$ATBRGL2 %in% c(1, 3) & df$GENRE %in% c(0, 1), ]
# Create contingency table for 'Strongly Agree' vs 'Strongly Disagree'
table_atbrgl2_scenario1 <- table(df_filtered_atbrgl2_scenario1$ATBRGL2, df_filtered_atbrgl2_scenario1$GENRE)
# Add descriptive labels to rows and columns
rownames(table_atbrgl2_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl2_scenario1) <- c("Female", "Male")
# Perform Chi-Squared test
chi_result_atbrgl2_scenario1 <- chisq.test(table_atbrgl2_scenario1)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl2_scenario1 <- oddsratio(table_atbrgl2_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl2_scenario1, caption = "Contingency Table: Gender vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl2_scenario1)
print(odds_ratio_atbrgl2_scenario1)

############################# 2nd scenario Neither agree nor desagree vs. Strongly Agree
# Filter for 'Strongly Agree' (3) and 'Neither Agree Nor Disagree' (2) responses for ATBRGL2
df_filtered_atbrgl2_scenario2 <- df[df$ATBRGL2 %in% c(2, 3) & df$GENRE %in% c(0, 1), ]
# Create contingency table for 'Strongly Agree' vs 'Neither Agree Nor Disagree'
table_atbrgl2_scenario2 <- table(df_filtered_atbrgl2_scenario2$ATBRGL2, df_filtered_atbrgl2_scenario2$GENRE)
# Add descriptive labels
rownames(table_atbrgl2_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl2_scenario2) <- c("Female", "Male")
# Perform Chi-Squared test
chi_result_atbrgl2_scenario2 <- chisq.test(table_atbrgl2_scenario2)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl2_scenario2 <- oddsratio(table_atbrgl2_scenario2, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl2_scenario2, caption = "Contingency Table: Gender vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl2_scenario2)
print(odds_ratio_atbrgl2_scenario2)


############################# 3rd scenario Neither agree nor desagree + Stringly Disagree vs. Strongly Agree
# Filter for 'Strongly Agree' (3), 'Strongly Disagree' (1) and 'Neither Agree Nor Disagree' (2) responses for ATBRGL2
df_filtered_atbrgl2_scenario3 <- df[df$ATBRGL2 %in% c(1, 2, 3) & df$GENRE %in% c(0, 1), ]
# Create a new variable for the combined 'Strongly Disagree' and 'Neither Agree Nor Disagree' condition
df_filtered_atbrgl2_scenario3$Disagree_Neither <- df_filtered_atbrgl2_scenario3$ATBRGL2 %in% c(1, 2)
# Create contingency table for 'Strongly Agree' vs 'Strongly Disagree + Neither Agree Nor Disagree'
table_atbrgl2_scenario3 <- table(df_filtered_atbrgl2_scenario3$Disagree_Neither, df_filtered_atbrgl2_scenario3$GENRE)
# Add descriptive labels
rownames(table_atbrgl2_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl2_scenario3) <- c("Female", "Male")
# Perform the Chi-Squared test
chi_result_atbrgl2_scenario3 <- chisq.test(table_atbrgl2_scenario3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl2_scenario3 <- oddsratio(table_atbrgl2_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl2_scenario3, caption = "Contingency Table: Gender vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl2_scenario3)
print(odds_ratio_atbrgl2_scenario3)

--------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL3 Parents should make sure all of their children’s vaccinations are up-to-date 
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)

####1st scenario
# Load dataframe
df <- Database_simplified
# Filter for 'Strongly Agree' (3) and 'Strongly Disagree' (1) responses for ATBRGL3 and genders 'Female' (0) and 'Male' (1)
df_filtered_atbrgl3_scenario1 <- df[df$ATBRGL3 %in% c(1, 3) & df$GENRE %in% c(0, 1), ]
# Create the contingency table for 'Strongly Agree' vs 'Strongly Disagree'
table_atbrgl3_scenario1 <- table(df_filtered_atbrgl3_scenario1$ATBRGL3, df_filtered_atbrgl3_scenario1$GENRE)
# Add descriptive labels to rows and columns
rownames(table_atbrgl3_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl3_scenario1) <- c("Female", "Male")
# Perform Chi-Squared test
chi_result_atbrgl3_scenario1 <- chisq.test(table_atbrgl3_scenario1)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl3_scenario1 <- oddsratio(table_atbrgl3_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl3_scenario1, caption = "Contingency Table: Gender vs. Opinion on Children's Vaccinations (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl3_scenario1)
print(odds_ratio_atbrgl3_scenario1)

### 2nd Scenario
# Filter for 'Strongly Agree' (3) and 'Neither Agree Nor Disagree' (2) responses for ATBRGL3
df_filtered_atbrgl3_scenario2 <- df[df$ATBRGL3 %in% c(2, 3) & df$GENRE %in% c(0, 1), ]
# Create contingency table for 'Strongly Agree' vs 'Neither Agree Nor Disagree'
table_atbrgl3_scenario2 <- table(df_filtered_atbrgl3_scenario2$ATBRGL3, df_filtered_atbrgl3_scenario2$GENRE)
# Add descriptive labels
rownames(table_atbrgl3_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl3_scenario2) <- c("Female", "Male")
# Perform Chi-Squared test
chi_result_atbrgl3_scenario2 <- chisq.test(table_atbrgl3_scenario2)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl3_scenario2 <- oddsratio(table_atbrgl3_scenario2, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl3_scenario2, caption = "Contingency Table: Gender vs. Opinion on Children's Vaccinations (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl3_scenario2)
print(odds_ratio_atbrgl3_scenario2)

## 3rd scenario
# Filter for 'Strongly Agree' (3), 'Strongly Disagree' (1) and 'Neither Agree Nor Disagree' (2) responses for ATBRGL3
df_filtered_atbrgl3_scenario3 <- df[df$ATBRGL3 %in% c(1, 2, 3) & df$GENRE %in% c(0, 1), ]
# Create a new variable for the combined 'Strongly Disagree' and 'Neither Agree Nor Disagree' condition
df_filtered_atbrgl3_scenario3$Disagree_Neither <- df_filtered_atbrgl3_scenario3$ATBRGL3 %in% c(1, 2)
# Create contingency table for 'Strongly Agree' vs 'Strongly Disagree + Neither Agree Nor Disagree'
table_atbrgl3_scenario3 <- table(df_filtered_atbrgl3_scenario3$Disagree_Neither, df_filtered_atbrgl3_scenario3$GENRE)
# Add descriptive labels
rownames(table_atbrgl3_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl3_scenario3) <- c("Female", "Male")
# Perform the Chi-Squared test
chi_result_atbrgl3_scenario3 <- chisq.test(table_atbrgl3_scenario3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl3_scenario3 <- oddsratio(table_atbrgl3_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl3_scenario3, caption = "Contingency Table: Gender vs. Opinion on Children's Vaccinations (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl3_scenario3)
print(odds_ratio_atbrgl3_scenario3)

---------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL4 People should wash their hands regularly
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

## Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_atbrgl4_scenario1 <- df[df$ATBRGL4 %in% c(1, 3) & df$GENRE %in% c(0, 1), ]
table_atbrgl4_scenario1 <- table(df_filtered_atbrgl4_scenario1$ATBRGL4, df_filtered_atbrgl4_scenario1$GENRE)
rownames(table_atbrgl4_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl4_scenario1) <- c("Female", "Male")
chi_result_atbrgl4_scenario1 <- chisq.test(table_atbrgl4_scenario1)
odds_ratio_atbrgl4_scenario1 <- oddsratio(table_atbrgl4_scenario1, conf.level = 0.95)$measure
print(kable(table_atbrgl4_scenario1, caption = "Contingency Table: Gender vs. Hand Washing Importance (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl4_scenario1)
print(odds_ratio_atbrgl4_scenario1)

## Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl4_scenario2 <- df[df$ATBRGL4 %in% c(2, 3) & df$GENRE %in% c(0, 1), ]
table_atbrgl4_scenario2 <- table(df_filtered_atbrgl4_scenario2$ATBRGL4, df_filtered_atbrgl4_scenario2$GENRE)
rownames(table_atbrgl4_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl4_scenario2) <- c("Female", "Male")
chi_result_atbrgl4_scenario2 <- chisq.test(table_atbrgl4_scenario2)
odds_ratio_atbrgl4_scenario2 <- oddsratio(table_atbrgl4_scenario2, conf.level = 0.95)$measure
print(kable(table_atbrgl4_scenario2, caption = "Contingency Table: Gender vs. Hand Washing Importance (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl4_scenario2)
print(odds_ratio_atbrgl4_scenario2)

## Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl4_scenario3 <- df[df$ATBRGL4 %in% c(1, 2, 3) & df$GENRE %in% c(0, 1), ]
df_filtered_atbrgl4_scenario3$Disagree_Neither <- df_filtered_atbrgl4_scenario3$ATBRGL4 %in% c(1, 2)
table_atbrgl4_scenario3 <- table(df_filtered_atbrgl4_scenario3$Disagree_Neither, df_filtered_atbrgl4_scenario3$GENRE)
rownames(table_atbrgl4_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl4_scenario3) <- c("Female", "Male")
chi_result_atbrgl4_scenario3 <- chisq.test(table_atbrgl4_scenario3)
odds_ratio_atbrgl4_scenario3 <- oddsratio(table_atbrgl4_scenario3, conf.level = 0.95)$measure
print(kable(table_atbrgl4_scenario3, caption = "Contingency Table: Gender vs. Hand Washing Importance (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl4_scenario3)
print(odds_ratio_atbrgl4_scenario3)

---------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL5 Doctors should only prescribe antibiotics when they are needed 
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)

# Load the Database_simplified dataframe
df <- Database_simplified

## Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_atbrgl5_scenario1 <- df[df$ATBRGL5 %in% c(1, 3) & df$GENRE %in% c(0, 1), ]
table_atbrgl5_scenario1 <- table(df_filtered_atbrgl5_scenario1$ATBRGL5, df_filtered_atbrgl5_scenario1$GENRE)
rownames(table_atbrgl5_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl5_scenario1) <- c("Female", "Male")
chi_result_atbrgl5_scenario1 <- chisq.test(table_atbrgl5_scenario1)
odds_ratio_atbrgl5_scenario1 <- oddsratio(table_atbrgl5_scenario1, conf.level = 0.95)$measure
print(kable(table_atbrgl5_scenario1, caption = "Contingency Table: Gender vs. Antibiotic Prescription Necessity (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl5_scenario1)
print(odds_ratio_atbrgl5_scenario1)

## Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl5_scenario2 <- df[df$ATBRGL5 %in% c(2, 3) & df$GENRE %in% c(0, 1), ]
table_atbrgl5_scenario2 <- table(df_filtered_atbrgl5_scenario2$ATBRGL5, df_filtered_atbrgl5_scenario2$GENRE)
rownames(table_atbrgl5_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl5_scenario2) <- c("Female", "Male")
chi_result_atbrgl5_scenario2 <- chisq.test(table_atbrgl5_scenario2)
odds_ratio_atbrgl5_scenario2 <- oddsratio(table_atbrgl5_scenario2, conf.level = 0.95)$measure
print(kable(table_atbrgl5_scenario2, caption = "Contingency Table: Gender vs. Antibiotic Prescription Necessity (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl5_scenario2)
print(odds_ratio_atbrgl5_scenario2)

## Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl5_scenario3 <- df[df$ATBRGL5 %in% c(1, 2, 3) & df$GENRE %in% c(0, 1), ]
df_filtered_atbrgl5_scenario3$Disagree_Neither <- df_filtered_atbrgl5_scenario3$ATBRGL5 %in% c(1, 2)
table_atbrgl5_scenario3 <- table(df_filtered_atbrgl5_scenario3$Disagree_Neither, df_filtered_atbrgl5_scenario3$GENRE)
rownames(table_atbrgl5_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl5_scenario3) <- c("Female", "Male")
chi_result_atbrgl5_scenario3 <- chisq.test(table_atbrgl5_scenario3)
odds_ratio_atbrgl5_scenario3 <- oddsratio(table_atbrgl5_scenario3, conf.level = 0.95)$measure
print(kable(table_atbrgl5_scenario3, caption = "Contingency Table: Gender vs. Antibiotic Prescription Necessity (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl5_scenario3)
print(odds_ratio_atbrgl5_scenario3)

----------------------------------------------------------------------------------------------------------------------
  
  ##ATBRGL6= People should only use antibiotics when prescribed by a doctor or nurse
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

## Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_atbrgl6_scenario1 <- df[df$ATBRGL6 %in% c(1, 3) & df$GENRE %in% c(0, 1), ]
table_atbrgl6_scenario1 <- table(df_filtered_atbrgl6_scenario1$ATBRGL6, df_filtered_atbrgl6_scenario1$GENRE)
rownames(table_atbrgl6_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl6_scenario1) <- c("Female", "Male")
chi_result_atbrgl6_scenario1 <- chisq.test(table_atbrgl6_scenario1)
odds_ratio_atbrgl6_scenario1 <- oddsratio(table_atbrgl6_scenario1, conf.level = 0.95)$measure
print(kable(table_atbrgl6_scenario1, caption = "Contingency Table: Gender vs. Antibiotic only when prescribed (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl6_scenario1)
print(odds_ratio_atbrgl6_scenario1)

## Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl6_scenario2 <- df[df$ATBRGL6 %in% c(2, 3) & df$GENRE %in% c(0, 1), ]
table_atbrgl6_scenario2 <- table(df_filtered_atbrgl6_scenario2$ATBRGL6, df_filtered_atbrgl6_scenario2$GENRE)
rownames(table_atbrgl6_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl6_scenario2) <- c("Female", "Male")
chi_result_atbrgl6_scenario2 <- chisq.test(table_atbrgl6_scenario2)
odds_ratio_atbrgl6_scenario2 <- oddsratio(table_atbrgl6_scenario2, conf.level = 0.95)$measure
print(kable(table_atbrgl6_scenario2, caption = "Contingency Table: Gender vs. Antibiotic only when prescribed (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl6_scenario2)
print(odds_ratio_atbrgl6_scenario2)

## Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl6_scenario3 <- df[df$ATBRGL6 %in% c(1, 2, 3) & df$GENRE %in% c(0, 1), ]
df_filtered_atbrgl6_scenario3$Disagree_Neither <- df_filtered_atbrgl6_scenario3$ATBRGL6 %in% c(1, 2)
table_atbrgl6_scenario3 <- table(df_filtered_atbrgl6_scenario3$Disagree_Neither, df_filtered_atbrgl6_scenario3$GENRE)
rownames(table_atbrgl6_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl6_scenario3) <- c("Female", "Male")
chi_result_atbrgl6_scenario3 <- chisq.test(table_atbrgl6_scenario3)
odds_ratio_atbrgl6_scenario3 <- oddsratio(table_atbrgl6_scenario3, conf.level = 0.95)$measure
print(kable(table_atbrgl6_scenario3, caption = "Contingency Table: Gender vs. Antibiotic only when prescribed (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl6_scenario3)
print(odds_ratio_atbrgl6_scenario3)

----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM1= Antibiotic resistance is one of the biggest problems the world faces
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_resdim1_scenario1 <- df[df$RESDIM1 %in% c(1, 3) & df$GENRE %in% c(0, 1), ]
table_resdim1_scenario1 <- table(df_filtered_resdim1_scenario1$RESDIM1, df_filtered_resdim1_scenario1$GENRE)
rownames(table_resdim1_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim1_scenario1) <- c("Female", "Male")
chi_result_resdim1_scenario1 <- chisq.test(table_resdim1_scenario1)
odds_ratio_resdim1_scenario1 <- oddsratio(table_resdim1_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim1_scenario1, caption = "Contingency Table: Gender vs. Perception of Antibiotic Resistance as a Global Problem (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_resdim1_scenario1)
print(odds_ratio_resdim1_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim1_scenario2 <- df[df$RESDIM1 %in% c(2, 3) & df$GENRE %in% c(0, 1), ]
table_resdim1_scenario2 <- table(df_filtered_resdim1_scenario2$RESDIM1, df_filtered_resdim1_scenario2$GENRE)
rownames(table_resdim1_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_resdim1_scenario2) <- c("Female", "Male")
chi_result_resdim1_scenario2 <- chisq.test(table_resdim1_scenario2)
odds_ratio_resdim1_scenario2 <- oddsratio(table_resdim1_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim1_scenario2, caption = "Contingency Table: Gender vs. Perception of Antibiotic Resistance as a Global Problem (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim1_scenario2)
print(odds_ratio_resdim1_scenario2)

# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim1_scenario3 <- df[df$RESDIM1 %in% c(1, 2, 3) & df$GENRE %in% c(0, 1), ]
df_filtered_resdim1_scenario3$Disagree_Neither <- df_filtered_resdim1_scenario3$RESDIM1 %in% c(1, 2)
table_resdim1_scenario3 <- table(df_filtered_resdim1_scenario3$Disagree_Neither, df_filtered_resdim1_scenario3$GENRE)
rownames(table_resdim1_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_resdim1_scenario3) <- c("Female", "Male")
chi_result_resdim1_scenario3 <- chisq.test(table_resdim1_scenario3)
odds_ratio_resdim1_scenario3 <- oddsratio(table_resdim1_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim1_scenario3, caption = "Contingency Table: Gender vs. Perception of Antibiotic Resistance as a Global Problem (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_resdim1_scenario3)
print(odds_ratio_resdim1_scenario3)

----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM2= Medical experts will solve the problem of antibiotic resistance before it becomes too serious 
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Load the Database_simplified dataframe
df <- read_excel("C:/Database_simplified.xlsx")

# Scenario 1: Strongly Agree vs. Strongly Disagree
df_filtered_resdim2_scenario1 <- df[df$RESDIM2 %in% c(1, 3) & df$GENRE %in% c(0, 1), ]
table_resdim2_scenario1 <- table(df_filtered_resdim2_scenario1$RESDIM2, df_filtered_resdim2_scenario1$GENRE)
rownames(table_resdim2_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim2_scenario1) <- c("Female", "Male")
chi_result_resdim2_scenario1 <- chisq.test(table_resdim2_scenario1)
odds_ratio_resdim2_scenario1 <- oddsratio(table_resdim2_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim2_scenario1, caption = "Contingency Table: Gender vs. Belief in Solving Antibiotic Resistance (Strongly Disagree vs. Strongly Agree)"))
print(chi_result_resdim2_scenario1)
print(odds_ratio_resdim2_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim2_scenario2 <- df[df$RESDIM2 %in% c(1, 2) & df$GENRE %in% c(0, 1), ]
table_resdim2_scenario2 <- table(df_filtered_resdim2_scenario2$RESDIM2, df_filtered_resdim2_scenario2$GENRE)
rownames(table_resdim2_scenario2) <- c("Strongly Disagree", "Neither Agree Nor Disagree")
colnames(table_resdim2_scenario2) <- c("Female", "Male")
chi_result_resdim2_scenario2 <- chisq.test(table_resdim2_scenario2)
odds_ratio_resdim2_scenario2 <- oddsratio(table_resdim2_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim2_scenario2, caption = "Contingency Table: Gender vs. Belief in Solving Antibiotic Resistance (Strongly Disagree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim2_scenario2)
print(odds_ratio_resdim2_scenario2)

# Scenario 3: Strongly Agree + Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim2_scenario3 <- df[df$RESDIM2 %in% c(1, 2, 3) & df$GENRE %in% c(0, 1), ]
df_filtered_resdim2_scenario3$Agree_Neither <- df_filtered_resdim2_scenario3$RESDIM2 %in% c(2, 3)
table_resdim2_scenario3 <- table(df_filtered_resdim2_scenario3$Agree_Neither, df_filtered_resdim2_scenario3$GENRE)
rownames(table_resdim2_scenario3) <- c("Strongly Disagree", "Strongly Agree + Neither")
colnames(table_resdim2_scenario3) <- c("Female", "Male")
chi_result_resdim2_scenario3 <- chisq.test(table_resdim2_scenario3)
odds_ratio_resdim2_scenario3 <- oddsratio(table_resdim2_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim2_scenario3, caption = "Contingency Table: Gender vs. Belief in Solving Antibiotic Resistance (Strongly Disagree vs. Strongly Agree + Neither Agree Nor Disagree)"))
print(chi_result_resdim2_scenario3)
print(odds_ratio_resdim2_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM3= Everyone needs to use antibiotics responsibly
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_resdim3_scenario1 <- df[df$RESDIM3 %in% c(1, 3) & df$GENRE %in% c(0, 1), ]
table_resdim3_scenario1 <- table(df_filtered_resdim3_scenario1$RESDIM3, df_filtered_resdim3_scenario1$GENRE)
rownames(table_resdim3_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim3_scenario1) <- c("Female", "Male")
chi_result_resdim3_scenario1 <- chisq.test(table_resdim3_scenario1)
odds_ratio_resdim3_scenario1 <- oddsratio(table_resdim3_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim3_scenario1, caption = "Contingency Table: Gender vs. Everyone needs to use antibiotics responsibly (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_resdim3_scenario1)
print(odds_ratio_resdim3_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim3_scenario2 <- df[df$RESDIM3 %in% c(2, 3) & df$GENRE %in% c(0, 1), ]
table_resdim3_scenario2 <- table(df_filtered_resdim3_scenario2$RESDIM3, df_filtered_resdim3_scenario2$GENRE)
rownames(table_resdim3_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_resdim3_scenario2) <- c("Female", "Male")
chi_result_resdim3_scenario2 <- chisq.test(table_resdim3_scenario2)
odds_ratio_resdim3_scenario2 <- oddsratio(table_resdim3_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim3_scenario2, caption = "Contingency Table: Gender vs. Everyone needs to use antibiotics responsibly (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim3_scenario2)
print(odds_ratio_resdim3_scenario2)

# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim3_scenario3 <- df[df$RESDIM3 %in% c(1, 2, 3) & df$GENRE %in% c(0, 1), ]
df_filtered_resdim3_scenario3$Disagree_Neither <- df_filtered_resdim3_scenario3$RESDIM3 %in% c(1, 2)
table_resdim3_scenario3 <- table(df_filtered_resdim3_scenario3$Disagree_Neither, df_filtered_resdim3_scenario3$GENRE)
rownames(table_resdim3_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_resdim3_scenario3) <- c("Female", "Male")
chi_result_resdim3_scenario3 <- chisq.test(table_resdim3_scenario3)
odds_ratio_resdim3_scenario3 <- oddsratio(table_resdim3_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim3_scenario3, caption = "Contingency Table: Gender vs. Everyone needs to use antibiotics responsibly (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_resdim3_scenario3)
print(odds_ratio_resdim3_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM4= People like me can't do much to stop antibiotic resistance
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Agree vs. Strongly Disagree
df_filtered_resdim4_scenario1 <- df[df$RESDIM4 %in% c(1, 3) & df$GENRE %in% c(0, 1), ]
table_resdim4_scenario1 <- table(df_filtered_resdim4_scenario1$RESDIM4, df_filtered_resdim4_scenario1$GENRE)
rownames(table_resdim4_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim4_scenario1) <- c("Female", "Male")
chi_result_resdim4_scenario1 <- chisq.test(table_resdim4_scenario1)
odds_ratio_resdim4_scenario1 <- oddsratio(table_resdim4_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim4_scenario1, caption = "Contingency Table: Gender vs. Belief in Individual Impact on Antibiotic Resistance (Strongly Disagree vs. Strongly Agree)"))
print(chi_result_resdim4_scenario1)
print(odds_ratio_resdim4_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim4_scenario2 <- df[df$RESDIM4 %in% c(1, 2) & df$GENRE %in% c(0, 1), ]
table_resdim4_scenario2 <- table(df_filtered_resdim4_scenario2$RESDIM4, df_filtered_resdim4_scenario2$GENRE)
rownames(table_resdim4_scenario2) <- c("Strongly Disagree", "Neither Agree Nor Disagree")
colnames(table_resdim4_scenario2) <- c("Female", "Male")
chi_result_resdim4_scenario2 <- chisq.test(table_resdim4_scenario2)
odds_ratio_resdim4_scenario2 <- oddsratio(table_resdim4_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim4_scenario2, caption = "Contingency Table: Gender vs. Belief in Individual Impact on Antibiotic Resistance (Strongly Disagree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim4_scenario2)
print(odds_ratio_resdim4_scenario2)

# Scenario 3: Strongly Agree + Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim4_scenario3 <- df[df$RESDIM4 %in% c(1, 2, 3) & df$GENRE %in% c(0, 1), ]
df_filtered_resdim4_scenario3$Agree_Neither <- df_filtered_resdim4_scenario3$RESDIM4 %in% c(2, 3)
table_resdim4_scenario3 <- table(df_filtered_resdim4_scenario3$Agree_Neither, df_filtered_resdim4_scenario3$GENRE)
rownames(table_resdim4_scenario3) <- c("Strongly Disagree", "Strongly Agree + Neither")
colnames(table_resdim4_scenario3) <- c("Female", "Male")
chi_result_resdim4_scenario3 <- chisq.test(table_resdim4_scenario3)
odds_ratio_resdim4_scenario3 <- oddsratio(table_resdim4_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim4_scenario3, caption = "Contingency Table: Gender vs. Belief in Individual Impact on Antibiotic Resistance (Strongly Disagree vs. Strongly Agree + Neither Agree Nor Disagree)"))
print(chi_result_resdim4_scenario3)
print(odds_ratio_resdim4_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM5= I am worried about the impact that antibiotic resistance will have on my health and that of my family
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_resdim5_scenario1 <- df[df$RESDIM5 %in% c(1, 3) & df$GENRE %in% c(0, 1), ]
table_resdim5_scenario1 <- table(df_filtered_resdim5_scenario1$RESDIM5, df_filtered_resdim5_scenario1$GENRE)
rownames(table_resdim5_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim5_scenario1) <- c("Female", "Male")
chi_result_resdim5_scenario1 <- chisq.test(table_resdim5_scenario1)
odds_ratio_resdim5_scenario1 <- oddsratio(table_resdim5_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim5_scenario1, caption = "Contingency Table: Gender vs. Impact of AMR on personal health and that of their family (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_resdim5_scenario1)
print(odds_ratio_resdim5_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim5_scenario2 <- df[df$RESDIM5 %in% c(2, 3) & df$GENRE %in% c(0, 1), ]
table_resdim5_scenario2 <- table(df_filtered_resdim5_scenario2$RESDIM5, df_filtered_resdim5_scenario2$GENRE)
rownames(table_resdim5_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_resdim5_scenario2) <- c("Female", "Male")
chi_result_resdim5_scenario2 <- chisq.test(table_resdim5_scenario2)
odds_ratio_resdim5_scenario2 <- oddsratio(table_resdim5_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim5_scenario2, caption = "Contingency Table: Gender vs. Impact of AMR on personal health and that of their family (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim5_scenario2)
print(odds_ratio_resdim5_scenario2)

# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim5_scenario3 <- df[df$RESDIM5 %in% c(1, 2, 3) & df$GENRE %in% c(0, 1), ]
df_filtered_resdim5_scenario3$Disagree_Neither <- df_filtered_resdim5_scenario3$RESDIM5 %in% c(1, 2)
table_resdim5_scenario3 <- table(df_filtered_resdim5_scenario3$Disagree_Neither, df_filtered_resdim5_scenario3$GENRE)
rownames(table_resdim5_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_resdim5_scenario3) <- c("Female", "Male")
chi_result_resdim5_scenario3 <- chisq.test(table_resdim5_scenario3)
odds_ratio_resdim5_scenario3 <- oddsratio(table_resdim5_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim5_scenario3, caption = "Contingency Table: Gender vs. Impact of AMR on personal health and that of their family (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_resdim5_scenario3)
print(odds_ratio_resdim5_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM6= I am not at risk of getting an antibiotic-resistant infection, as long as I take my antibiotics correctly
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Agree vs. Strongly Disagree
df_filtered_resdim6_scenario1 <- df[df$RESDIM6 %in% c(1, 3) & df$GENRE %in% c(0, 1), ]
table_resdim6_scenario1 <- table(df_filtered_resdim6_scenario1$RESDIM6, df_filtered_resdim6_scenario1$GENRE)
print(table_resdim6_scenario1)
rownames(table_resdim6_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim6_scenario1) <- c("Female", "Male")
chi_result_resdim6_scenario1 <- chisq.test(table_resdim6_scenario1)
odds_ratio_resdim6_scenario1 <- oddsratio(table_resdim6_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim6_scenario1, caption = "Contingency Table: Gender vs. Perception of Risk of Antibiotic-Resistant Infection (Strongly Disagree vs. Strongly Agree)"))
print(chi_result_resdim6_scenario1)
print(odds_ratio_resdim6_scenario1)
print(table_resdim6_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim6_scenario2 <- df[df$RESDIM6 %in% c(1, 2) & df$GENRE %in% c(0, 1), ]
table_resdim6_scenario2 <- table(df_filtered_resdim6_scenario2$RESDIM6, df_filtered_resdim6_scenario2$GENRE)
print(table_resdim6_scenario2)
rownames(table_resdim6_scenario2) <- c("Strongly Disagree", "Neither Agree Nor Disagree")
colnames(table_resdim6_scenario2) <- c("Female", "Male")
chi_result_resdim6_scenario2 <- chisq.test(table_resdim6_scenario2)
odds_ratio_resdim6_scenario2 <- oddsratio(table_resdim6_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim6_scenario2, caption = "Contingency Table: Gender vs. Perception of Risk of Antibiotic-Resistant Infection (Strongly Disagree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim6_scenario2)
print(odds_ratio_resdim6_scenario2)

# Scenario 3: Strongly Agree + Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim6_scenario3 <- df[df$RESDIM6 %in% c(1, 2, 3) & df$GENRE %in% c(0, 1), ]
df_filtered_resdim6_scenario3$Agree_Neither <- df_filtered_resdim6_scenario3$RESDIM6 %in% c(2, 3)
table_resdim6_scenario3 <- table(df_filtered_resdim6_scenario3$Agree_Neither, df_filtered_resdim6_scenario3$GENRE)
print(table_resdim6_scenario3)
rownames(table_resdim6_scenario3) <- c("Strongly Disagree", "Strongly Agree + Neither")
colnames(table_resdim6_scenario3) <- c("Female", "Male")
chi_result_resdim6_scenario3 <- chisq.test(table_resdim6_scenario3)
odds_ratio_resdim6_scenario3 <- oddsratio(table_resdim6_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim6_scenario3, caption = "Contingency Table: Gender vs. Perception of Risk of Antibiotic-Resistant Infection (Strongly Disagree vs. Strongly Agree + Neither Agree Nor Disagree)"))
print(chi_result_resdim6_scenario3)
print(odds_ratio_resdim6_scenario3)


############################################### Comparisons by Nationality (Canadian vs Other) #######################################

Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
---------------------------------------------------------------------------------------------------------------
  ##CUSIN1 (I wash my hands before cooking (No= 9.4%))
  
  # Ensure that the dataframe name is consistent
  df_filtered <- Database_simplified[Database_simplified$CUSIN1 %in% c(0, 1) & Database_simplified$CIT1 %in% c(0, 1), ]
# Create the contingency table
table <- table(df_filtered$CUSIN1, df_filtered$CIT1)
# Add descriptive labels to rows and columns
rownames(table) <- c("CUSIN1 (Yes)", "CUSIN1 (No)")
colnames(table) <- c("Canadian", "Other")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Nationality vs. Hand Washing")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

############ Verification using Fisher's test (in cases which one of the cells has 5 or less)
# Fisher's Exact Test for Count Data
#fisher_result <- fisher.test(table)
# Print the results of the Fisher's Exact Test
#print(fisher_result)
# Calculating the odds ratio for a 2x2 table
# Note: Odds ratios can be calculated from Fisher test objects as well
#odds_ratio <- fisher_result$estimate
# Calculating the confidence interval from the Fisher's Exact Test
#confidence_interval <- fisher_result$conf.int
# Printing the odds ratio and confidence interval
#print(odds_ratio)
#print(confidence_interval)

-------------------------------------------------------------------------------------------------------
  
  ##CUSIN2 (After handling raw food (meat and vegetables), I wash my hands with soap (No= 15.1%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
# Ensure that the dataframe name is consistent
df_filtered <- Database_simplified[Database_simplified$CUSIN2 %in% c(0, 1) & Database_simplified$CIT1 %in% c(0, 1), ]
# Create the contingency table
table <- table(df_filtered$CUSIN2, df_filtered$CIT1)
# Add descriptive labels to rows and columns
rownames(table) <- c("CUSIN2 (Yes)", "CUSIN2 (No)")
colnames(table) <- c("Canadian", "Other")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Nationality vs. After handling raw food (meat and vegetables), I wash my hands with soap")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN3 (I use the same kitchen utensils for handling raw and ready-to-eat foods (Yes=25.8%))
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
# Ensure that the dataframe name is consistent
df_filtered <- Database_simplified[Database_simplified$CUSIN3 %in% c(0, 1) & Database_simplified$CIT1 %in% c(0, 1), ]
# Create the contingency table
table <- table(df_filtered$CUSIN3, df_filtered$CIT1)
# Add descriptive labels to rows and columns
rownames(table) <- c("CUSIN3 (Yes)", "CUSIN3 (No)")
colnames(table) <- c("Canadian", "Other")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Nationality vs. I use the same kitchen utensils for handling raw and ready-to-eat foods")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

-------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN4 (I wash kitchen utensils that have been used for raw food before using them to prepare other foods  (No=16.8%))
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
# Ensure that the dataframe name is consistent
df_filtered <- Database_simplified[Database_simplified$CUSIN4 %in% c(0, 1) & Database_simplified$CIT1 %in% c(0, 1), ]
# Create the contingency table
table <- table(df_filtered$CUSIN4, df_filtered$CIT1)
# Add descriptive labels to rows and columns
rownames(table) <- c("CUSIN4 (Yes)", "CUSIN4 (No)")
colnames(table) <- c("Canadian", "Other")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Nationality vs. I wash kitchen utensils that have been used for raw food before using them to prepare other foods")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

-------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN5 (I wash fruits and vegetables before eating them (No=20.7%))
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
# Ensure that the dataframe name is consistent
df_filtered <- Database_simplified[Database_simplified$CUSIN5 %in% c(0, 1) & Database_simplified$CIT1 %in% c(0, 1), ]
# Create the contingency table
table <- table(df_filtered$CUSIN5, df_filtered$CIT1)
# Add descriptive labels to rows and columns
rownames(table) <- c("CUSIN5 (Yes)", "CUSIN5 (No)")
colnames(table) <- c("Canadian", "Other")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Nationality vs. I wash fruits and vegetables before eating them")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

-------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN6 (I wash my hands before eating (No=21.5))
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx") 
# Ensure that the dataframe name is consistent
df_filtered <- Database_simplified[Database_simplified$CUSIN6 %in% c(0, 1) & Database_simplified$CIT1 %in% c(0, 1), ]
# Create the contingency table
table <- table(df_filtered$CUSIN6, df_filtered$CIT1)
# Add descriptive labels to rows and columns
rownames(table) <- c("CUSIN6 (Yes)", "CUSIN6 (No)")
colnames(table) <- c("Canadian", "Other")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Nationality vs. I wash my hands before eating")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

----------------------------------------------------------------------------------------------------
  
  ##PRESCATB1 When you get a prescription for antibiotics, do you follow the recommended 
  ##length of treatment and daily dosage? (No=4.2%) (Sometimes=9.6%) (No+Sometimes=13.8%)
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)

############### 1st scenario= No
# Make sure 'Database_simplified' is the correct name of your dataframe
df <- Database_simplified
# Filter only 'Yes' and 'No' responses for PRESCATB1 and nationalities 'Canadian' and 'Other'
df_filtered_prescatb1 <- df[df$PRESCATB1 %in% c(0, 1) & df$CIT1 %in% c(0, 1), ]
# Create the contingency table
table_prescatb1 <- table(df_filtered_prescatb1$PRESCATB1, df_filtered_prescatb1$CIT1)
# Add descriptive labels to the rows and columns
rownames(table_prescatb1) <- c("Yes", "No")
colnames(table_prescatb1) <- c("Canadian", "Other")
# Perform the Chi-Squared test
chi_result_prescatb1 <- chisq.test(table_prescatb1)
# Calculate the odds ratio and confidence interval
odds_ratio_prescatb1 <- oddsratio(table_prescatb1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_prescatb1, caption = "Contingency Table: Nationality vs. Following Prescription for Antibiotics"))
# Print the results of the Chi-Squared test
print(chi_result_prescatb1)
# Print the odds ratio and confidence interval
print(odds_ratio_prescatb1)

############ Verification using Fisher's test (in cases which one of the cells has 5 or less)
# Fisher's Exact Test for Count Data
fisher_result <- fisher.test(table_prescatb1)
# Print the results of the Fisher's Exact Test
print(fisher_result)
# Calculating the odds ratio for a 2x2 table
# Note: Odds ratios can be calculated from Fisher test objects as well
odds_ratio <- fisher_result$estimate
# Calculating the confidence interval from the Fisher's Exact Test
confidence_interval <- fisher_result$conf.int
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

################## 2nd scenario= Sometimes
# Filter for 'Yes' and 'Sometimes' responses for PRESCATB1 and nationalities 'Female' and 'Male'
df_filtered_prescatb1_sometimes <- df[df$PRESCATB1 %in% c(0, 3) & df$CIT1 %in% c(0, 1), ]
# Create the contingency table for 'Yes' vs 'Sometimes'
table_prescatb1_sometimes <- table(df_filtered_prescatb1_sometimes$PRESCATB1, df_filtered_prescatb1_sometimes$CIT1)
# Adjust the table to have 'Yes' and 'Sometimes' as row names
# This step assumes that both 'Yes' and 'Sometimes' responses are present in the filtered data
if (all(c(0, 3) %in% df_filtered_prescatb1_sometimes$PRESCATB1)) {
  rownames(table_prescatb1_sometimes) <- c("Yes", "Sometimes")
} else {
  stop("Not all expected PRESCATB1 responses (Yes and Sometimes) are present in the filtered data.")
}
# Perform the Chi-Squared test
chi_result_prescatb1_sometimes <- chisq.test(table_prescatb1_sometimes)
# Calculate the odds ratio and confidence interval
odds_ratio_prescatb1_sometimes <- oddsratio(table_prescatb1_sometimes, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_prescatb1_sometimes, caption = "Contingency Table: Nationality vs. Following Prescription for Antibiotics Sometimes"))
# Print the results of the Chi-Squared test
print(chi_result_prescatb1_sometimes)
# Print the odds ratio and confidence interval
print(odds_ratio_prescatb1_sometimes)

############ Verification using Fisher's test (in cases which one of the cells has 5 or less)
# Fisher's Exact Test for Count Data
fisher_result <- fisher.test(table_prescatb1_sometimes)
# Print the results of the Fisher's Exact Test
print(fisher_result)
# Calculating the odds ratio for a 2x2 table
# Note: Odds ratios can be calculated from Fisher test objects as well
odds_ratio <- fisher_result$estimate
# Calculating the confidence interval from the Fisher's Exact Test
confidence_interval <- fisher_result$conf.int
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

################## 3rd scenario= No+Sometimes
# Filter for 'Yes', 'No', and 'Sometimes' responses for PRESCATB1 and nationality 'Canadian' and 'Other'
df_filtered_prescatb1_combined <- df[df$PRESCATB1 %in% c(0, 1, 3) & df$CIT1 %in% c(0, 1), ]
# Create a new variable for the combined 'No' and 'Sometimes' condition
df_filtered_prescatb1_combined$No_Sometimes <- df_filtered_prescatb1_combined$PRESCATB1 %in% c(1, 3)
# Create the contingency table for 'Yes' vs 'No+Sometimes'
table_prescatb1_combined <- table(df_filtered_prescatb1_combined$No_Sometimes, df_filtered_prescatb1_combined$CIT1)
# Adjust the table to have 'Yes' and 'No+Sometimes' as row names
rownames(table_prescatb1_combined) <- c("Yes", "No_Sometimes")
# Perform the Chi-Squared test
chi_result_prescatb1_combined <- chisq.test(table_prescatb1_combined)
# Calculate the odds ratio and confidence interval
odds_ratio_prescatb1_combined <- oddsratio(table_prescatb1_combined, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_prescatb1_combined, caption = "Contingency Table: Nationality vs. Following Prescription for Antibiotics (Yes vs. No+Sometimes)"))
# Print the results of the Chi-Squared test
print(chi_result_prescatb1_combined)
# Print the odds ratio and confidence interval
print(odds_ratio_prescatb1_combined)

---------------------------------------------------------------------------------------------------------------------
  
  ##ARRETATB Do you stop taking antibiotics when symptoms start to disappear?
  ##(Always=7.3%) (Sometimes=20.4%) (Always+Sometimes=27.7%)
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
df <- Database_simplified

############### 1st scenario= Always
# Filter for 'Always' and 'Never' responses for ARRETATB and nationalities 'Canadian' and 'Other'
df_filtered_arretatb <- df[df$ARRETATB %in% c(0, 1) & df$CIT1 %in% c(0, 1), ]
# Create the contingency table for 'Always' vs 'Never'
table_arretatb <- table(df_filtered_arretatb$ARRETATB, df_filtered_arretatb$CIT1)
# Add descriptive labels to the rows and columns
rownames(table_arretatb) <- c("Always", "Never")
colnames(table_arretatb) <- c("Canadian", "Other")
# Perform the Chi-Squared test
chi_result_arretatb <- chisq.test(table_arretatb)
# Calculate the odds ratio and confidence interval
odds_ratio_arretatb <- oddsratio(table_arretatb, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_arretatb, caption = "Contingency Table: Nationality vs. Stopping Antibiotics Always vs. Never"))
# Print the results of the Chi-Squared test
print(chi_result_arretatb)
# Print the odds ratio and confidence interval
print(odds_ratio_arretatb)

############ Verification using Fisher's test (in cases which one of the cells has 5 or less)
# Fisher's Exact Test for Count Data
fisher_result <- fisher.test(table_arretatb)
# Print the results of the Fisher's Exact Test
print(fisher_result)
# Calculating the odds ratio for a 2x2 table
# Note: Odds ratios can be calculated from Fisher test objects as well
odds_ratio <- fisher_result$estimate
# Calculating the confidence interval from the Fisher's Exact Test
confidence_interval <- fisher_result$conf.int
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

################# 2nd Cenario: Sometimes
# Filter for 'Sometimes' and 'Never' responses for ARRETATB and nationalities 'Canadian' and 'Other'
df_filtered_arretatb_sometimes <- df[df$ARRETATB %in% c(1, 2) & df$CIT1 %in% c(0, 1), ]
# Create the contingency table for 'Sometimes' vs 'Never'
table_arretatb_sometimes <- table(df_filtered_arretatb_sometimes$ARRETATB == 2, df_filtered_arretatb_sometimes$CIT1)
# Add descriptive labels to the rows and columns
rownames(table_arretatb_sometimes) <- c("Never", "Sometimes")
colnames(table_arretatb_sometimes) <- c("Canadian", "Other")
# Perform the Chi-Squared test
chi_result_arretatb_sometimes <- chisq.test(table_arretatb_sometimes)
# Calculate the odds ratio and confidence interval
odds_ratio_arretatb_sometimes <- oddsratio(table_arretatb_sometimes, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_arretatb_sometimes, caption = "Contingency Table: Nationality vs. Stopping Antibiotics Sometimes vs. Never"))
# Print the results of the Chi-Squared test
print(chi_result_arretatb_sometimes)
# Print the odds ratio and confidence interval
print(odds_ratio_arretatb_sometimes)

############### #3rd scenario= Sometimes+Always
# Filter for 'Always', 'Never', and 'Sometimes' responses for ARRETATB and nationalities 'Canadian' and 'Other'
df_filtered_arretatb_combined <- df[df$ARRETATB %in% c(0, 1, 2) & df$CIT1 %in% c(0, 1), ]
# Create a new variable for the combined 'Sometimes' and 'Always' condition
df_filtered_arretatb_combined$Sometimes_Always <- df_filtered_arretatb_combined$ARRETATB %in% c(0, 2)
# Create the contingency table for 'Sometimes+Always' vs 'Never'
table_arretatb_combined <- table(df_filtered_arretatb_combined$Sometimes_Always, df_filtered_arretatb_combined$CIT1)
# Add descriptive labels to the rows and columns
rownames(table_arretatb_combined) <- c("Never", "Sometimes_Always")
colnames(table_arretatb_combined) <- c("Canadian", "Other")
# Perform the Chi-Squared test
chi_result_arretatb_combined <- chisq.test(table_arretatb_combined)
# Calculate the odds ratio and confidence interval
odds_ratio_arretatb_combined <- oddsratio(table_arretatb_combined, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_arretatb_combined, caption = "Contingency Table: Nationality vs. Stopping Antibiotics (Sometimes+Always vs. Never)"))
# Print the results of the Chi-Squared test
print(chi_result_arretatb_combined)
# Print the odds ratio and confidence interval
print(odds_ratio_arretatb_combined)

---------------------------------------------------------------------------------------------------------------------
  
  ##ATBORAL1 Have you ever taken an oral antibiotic treatment (by mouth) without a medical prescription? (Yes=12.3%)
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
# Make sure 'Database_simplified' is the correct name of your dataframe
df <- Database_simplified
# Filter for 'Yes' and 'No' responses for ATBORAL and nationalities 'Canadian' and 'Other' 
df_filtered_atboral <- df[df$ATBORAL1 %in% c(0, 1) & df$CIT1 %in% c(0, 1), ]
# Create the contingency table for 'Yes' vs 'No'
table_atboral <- table(df_filtered_atboral$ATBORAL1, df_filtered_atboral$CIT1)
# Add descriptive labels to the rows and columns
rownames(table_atboral) <- c("Yes", "No")
colnames(table_atboral) <- c("Canadian", "Other")
# Perform the Chi-Squared test
chi_result_atboral <- chisq.test(table_atboral)
# Calculate the odds ratio and confidence interval
odds_ratio_atboral <- oddsratio(table_atboral, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atboral, caption = "Contingency Table: Nationality vs. Taking Oral Antibiotics Without Prescription (Yes vs. No)"))
# Print the results of the Chi-Squared test
print(chi_result_atboral)
# Print the odds ratio and confidence interval
print(odds_ratio_atboral)

--------------------------------------------------------------------------------------------------------
  
  ### ATBANI1 I can exchange resistant bacteria with my pet (False=23.2%)
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
# Make sure 'Database_simplified' is the correct name of your dataframe
df <- Database_simplified
# Filter for 'True' and 'False' responses for ATBANI1 and nationalities 'Canadian' and 'Other'
df_filtered_atbani1 <- df[df$ATBANI1 %in% c(0, 1) & df$CIT1 %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_atbani1 <- table(df_filtered_atbani1$ATBANI1, df_filtered_atbani1$CIT1)
# Add descriptive labels to the rows and columns
rownames(table_atbani1) <- c("True", "False")
colnames(table_atbani1) <- c("Canadian", "Other")
# Perform the Chi-Squared test
chi_result_atbani1 <- chisq.test(table_atbani1)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani1 <- oddsratio(table_atbani1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani1, caption = "Contingency Table: Nationality vs. Exchanging Resistant Bacteria with Pets (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani1)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani1)

---------------------------------------------------------------------------------------------------------------------
  
  ### ATBANI2=The use of antibiotics in livestock and crops can increase the 
  #presence of resistant bacteria in the environment (False=14.7%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")  
# Ensure 'Database_simplified' is the correct name of your dataframe
df <- Database_simplified
# Filter for 'True' and 'False' responses for ATBANI2 and nationalities 'Canadian' and 'Other'
df_filtered_atbani2 <- df[df$ATBANI2 %in% c(0, 1) & df$CIT1 %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_atbani2 <- table(df_filtered_atbani2$ATBANI2, df_filtered_atbani2$CIT1)
# Add descriptive labels to the rows and columns
rownames(table_atbani2) <- c("True", "False")
colnames(table_atbani2) <- c("canadian", "Other")
# Perform the Chi-Squared test
chi_result_atbani2 <- chisq.test(table_atbani2)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani2 <- oddsratio(table_atbani2, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani2, caption = "Contingency Table: Nationality vs. Antibiotics in Livestock and Crops Affecting Environment (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani2)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani2)

############ Verification using Fisher's test (in cases which one of the cells has 5 or less)
# Fisher's Exact Test for Count Data
fisher_result <- fisher.test(table_atbani2)
# Print the results of the Fisher's Exact Test
print(fisher_result)
# Calculating the odds ratio for a 2x2 table
# Note: Odds ratios can be calculated from Fisher test objects as well
odds_ratio <- fisher_result$estimate
# Calculating the confidence interval from the Fisher's Exact Test
confidence_interval <- fisher_result$conf.int
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

--------------------------------------------------------------------------------------------------------------------
  
  ##### ATBANI3	The use of antibiotics in livestock and crops can affect me directly
  ##(I can get resistant bacteria in my body) (False=26.3%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")  
# Ensure 'Database_simplified' is the correct name of your dataframe
df <- Database_simplified
# Filter for 'True' and 'False' responses for ATBANI3 and nationalities 'Canadian' and 'Other'
df_filtered_atbani3 <- df[df$ATBANI3 %in% c(0, 1) & df$CIT1 %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_atbani3 <- table(df_filtered_atbani3$ATBANI3, df_filtered_atbani3$CIT1)
# Add descriptive labels to the rows and columns
rownames(table_atbani3) <- c("True", "False")
colnames(table_atbani3) <- c("Canadian", "Other")
# Perform the Chi-Squared test
chi_result_atbani3 <- chisq.test(table_atbani3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani3 <- oddsratio(table_atbani3, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani3, caption = "Contingency Table: Nationality vs. Antibiotics in Livestock and Crops Affecting Humans Directly (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani3)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani3)

-------------------------------------------------------------------------------------------------------------------
  ##### ATBANI4	Resistant bacteria are only found in hospitals (True=10.8%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")  
# Ensure 'Database_simplified' is the correct name of your dataframe
df <- Database_simplified
# Filter for 'True' and 'False' responses for ATBANI4 and nationalities 'Canadian' and 'Other'
df_filtered_atbani4 <- df[df$ATBANI4 %in% c(0, 1) & df$CIT1 %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_atbani4 <- table(df_filtered_atbani4$ATBANI4, df_filtered_atbani4$CIT1)
# Add descriptive labels to the rows and columns
rownames(table_atbani4) <- c("True", "False")
colnames(table_atbani4) <- c("Canadian", "Other")
# Perform the Chi-Squared test
chi_result_atbani4 <- chisq.test(table_atbani4)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani4 <- oddsratio(table_atbani4, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani4, caption = "Contingency Table: Nationality vs. Resistant Bacteria Found Only in Hospitals (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani4)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani4)

----------------------------------------------------------------------------------------------------------------------
  #####RESATB1	Antibiotic resistance occurs when your body becomes resistant to antibiotics and they
  ##no longer work as well (True=58.3%)
  
  # Load the database
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified
# Filter for 'True' and 'False' responses for RESATB1 and nationalities 'Canadian' and 'Other'
df_filtered_resatb1 <- df[df$RESATB1 %in% c(0, 1) & df$CIT1 %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_resatb1 <- table(df_filtered_resatb1$RESATB1, df_filtered_resatb1$CIT1)
# Add descriptive labels to rows and columns
rownames(table_resatb1) <- c("True", "False")
colnames(table_resatb1) <- c("Canadian", "Other")
# Perform the Chi-Squared test
chi_result_resatb1 <- chisq.test(table_resatb1)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb1 <- oddsratio(table_resatb1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb1, caption = "Contingency Table: Nationality vs. Understanding of Antibiotic Resistance (RESATB1: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb1)
print(odds_ratio_resatb1)

-------------------------------------------------------------------------------------------------------------------
  #####RESATB2	Many infections are becoming increasingly resistant to antibiotic treatment  (False=12.5%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
# Load the database
df <- Database_simplified
# Filter for 'True' and 'False' responses for RESATB2 and nationalities 'Canadian' and 'Other'
df_filtered_resatb2 <- df[df$RESATB2 %in% c(0, 1) & df$CIT1 %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_resatb2 <- table(df_filtered_resatb2$RESATB2, df_filtered_resatb2$CIT1)
# Add descriptive labels to rows and columns
rownames(table_resatb2) <- c("True", "False")
colnames(table_resatb2) <- c("Canadian", "Other")
# Perform the Chi-Squared test
chi_result_resatb2 <- chisq.test(table_resatb2)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb2 <- oddsratio(table_resatb2, conf.level = 0.95)$measure
# Print the formatted contingency table and test results
print(kable(table_resatb2, caption = "Contingency Table: Nationality vs. Perception of Increasing Infection Resistance (RESATB2: True vs. False)"))
print(chi_result_resatb2)
print(odds_ratio_resatb2)

############ Verification using Fisher's test (in cases which one of the cells has 5 or less)
# Fisher's Exact Test for Count Data
fisher_result <- fisher.test(table_resatb2)
# Print the results of the Fisher's Exact Test
print(fisher_result)
# Calculating the odds ratio for a 2x2 table
# Note: Odds ratios can be calculated from Fisher test objects as well
odds_ratio <- fisher_result$estimate
# Calculating the confidence interval from the Fisher's Exact Test
confidence_interval <- fisher_result$conf.int
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)


---------------------------------------------------------------------------------------------------------------------
  #####RESATB3	If bacteria are resistant to antibiotics, it can be very difficult or impossible to treat the infections they cause (False=16.7%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
# Load the database
df <- Database_simplified
# Filter for 'True' and 'False' responses for RESATB3 and nationalities 'Canadian' and 'Other'
df_filtered_resatb3 <- df[df$RESATB3 %in% c(0, 1) & df$CIT1 %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_resatb3 <- table(df_filtered_resatb3$RESATB3, df_filtered_resatb3$CIT1)
# Add descriptive labels to rows and columns
rownames(table_resatb3) <- c("True", "False")
colnames(table_resatb3) <- c("Canadian", "Other")
# Perform the Chi-Squared test
chi_result_resatb3 <- chisq.test(table_resatb3)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb3 <- oddsratio(table_resatb3, conf.level = 0.95)$measure
# Print the formatted contingency table and test results
print(kable(table_resatb3, caption = "Contingency Table: Nationality vs. Perception of Difficulty Treating Infections (RESATB3: True vs. False)"))
print(chi_result_resatb3)
print(odds_ratio_resatb3)

############ Verification using Fisher's test (in cases which one of the cells has 5 or less)
# Fisher's Exact Test for Count Data
fisher_result <- fisher.test(table_resatb3)
# Print the results of the Fisher's Exact Test
print(fisher_result)
# Calculating the odds ratio for a 2x2 table
# Note: Odds ratios can be calculated from Fisher test objects as well
odds_ratio <- fisher_result$estimate
# Calculating the confidence interval from the Fisher's Exact Test
confidence_interval <- fisher_result$conf.int
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)


----------------------------------------------------------------------------------------------------------------------
  #####RESATB4	Antibiotic resistance is an issue that could affect me or my family (False=11.8%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
# Load the database
df <- Database_simplified
# Filter for 'True' and 'False' responses for RESATB4 and nationalities 'Canadian' and 'Other'
df_filtered_resatb4 <- df[df$RESATB4 %in% c(0, 1) & df$CIT1 %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_resatb4 <- table(df_filtered_resatb4$RESATB4, df_filtered_resatb4$CIT1)
# Add descriptive labels to rows and columns
rownames(table_resatb4) <- c("True", "False")
colnames(table_resatb4) <- c("Canadian", "Other")
# Perform the Chi-Squared test
chi_result_resatb4 <- chisq.test(table_resatb4)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb4 <- oddsratio(table_resatb4, conf.level = 0.95)$measure
# Print the formatted contingency table and test results
print(kable(table_resatb4, caption = "Contingency Table: Nationality vs. Perception of Antibiotic Resistance Affecting One's Family (RESATB4: True vs. False)"))
print(chi_result_resatb4)
print(odds_ratio_resatb4)

############ Verification using Fisher's test (in cases which one of the cells has 5 or less)
# Fisher's Exact Test for Count Data
fisher_result <- fisher.test(table_resatb4)
# Print the results of the Fisher's Exact Test
print(fisher_result)
# Calculating the odds ratio for a 2x2 table
# Note: Odds ratios can be calculated from Fisher test objects as well
odds_ratio <- fisher_result$estimate
# Calculating the confidence interval from the Fisher's Exact Test
confidence_interval <- fisher_result$conf.int
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)


---------------------------------------------------------------------------------------------------------------------
  #####RESATB5	Antibiotic resistance is an issue in other countries but not here (True=9.9%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
# Load the database
df <- Database_simplified
# Filter for 'True' and 'False' responses for RESATB5 and nationalities 'Canadian' and 'Other'
df_filtered_resatb5 <- df[df$RESATB5 %in% c(0, 1) & df$CIT1 %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_resatb5 <- table(df_filtered_resatb5$RESATB5, df_filtered_resatb5$CIT1)
# Add descriptive labels to rows and columns
rownames(table_resatb5) <- c("True", "False")
colnames(table_resatb5) <- c("Canadian", "Other")
# Perform the Chi-Squared test
chi_result_resatb5 <- chisq.test(table_resatb5)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb5 <- oddsratio(table_resatb5, conf.level = 0.95)$measure
# Print the formatted contingency table and test results
print(kable(table_resatb5, caption = "Contingency Table: Nationality vs. Perception of Antibiotic Resistance as an Issue Only in Other Countries (RESATB5: True vs. False)"))
print(chi_result_resatb5)
print(odds_ratio_resatb5)

############ Verification using Fisher's test (in cases which one of the cells has 5 or less)
# Fisher's Exact Test for Count Data
fisher_result <- fisher.test(table_resatb5)
# Print the results of the Fisher's Exact Test
print(fisher_result)
# Calculating the odds ratio for a 2x2 table
# Note: Odds ratios can be calculated from Fisher test objects as well
odds_ratio <- fisher_result$estimate
# Calculating the confidence interval from the Fisher's Exact Test
confidence_interval <- fisher_result$conf.int
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)


---------------------------------------------------------------------------------------------------------------------  
  #####RESATB6	Antibiotic resistance is only a problem for people who take antibiotics regularly (True=17.5%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
# Load the database
df <- Database_simplified
# Filter for 'True' and 'False' responses for RESATB6 and nationalities 'Canadian' and 'Other'
df_filtered_resatb6 <- df[df$RESATB6 %in% c(0, 1) & df$CIT1 %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_resatb6 <- table(df_filtered_resatb6$RESATB6, df_filtered_resatb6$CIT1)
# Add descriptive labels to rows and columns
rownames(table_resatb6) <- c("True", "False")
colnames(table_resatb6) <- c("Canadian", "Other")
# Perform the Chi-Squared test
chi_result_resatb6 <- chisq.test(table_resatb6)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb6 <- oddsratio(table_resatb6, conf.level = 0.95)$measure
# Print the formatted contingency table and test results
print(kable(table_resatb6, caption = "Contingency Table: Nationality vs. Perception of Antibiotic Resistance as a Problem Only for Regular Antibiotic Users (RESATB6: True vs. False)"))
print(chi_result_resatb6)
print(odds_ratio_resatb6)

############ Verification using Fisher's test (in cases which one of the cells has 5 or less)
# Fisher's Exact Test for Count Data
fisher_result <- fisher.test(table_resatb6)
# Print the results of the Fisher's Exact Test
print(fisher_result)
# Calculating the odds ratio for a 2x2 table
# Note: Odds ratios can be calculated from Fisher test objects as well
odds_ratio <- fisher_result$estimate
# Calculating the confidence interval from the Fisher's Exact Test
confidence_interval <- fisher_result$conf.int
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

--------------------------------------------------------------------------------------------------------------------- 
  #####RESATB7	Bacteria that are resistant to antibiotics can be spread from person to person (False=20.2%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx") 

# Load the database
df <- Database_simplified
# Filter for 'True' and 'False' responses for RESATB7 and nationalities 'Canadian' and 'Other'
df_filtered_resatb7 <- df[df$RESATB7 %in% c(0, 1) & df$CIT1 %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_resatb7 <- table(df_filtered_resatb7$RESATB7, df_filtered_resatb7$CIT1)
# Add descriptive labels to rows and columns
rownames(table_resatb7) <- c("True", "False")
colnames(table_resatb7) <- c("Canadian", "Other")
# Perform the Chi-Squared test
chi_result_resatb7 <- chisq.test(table_resatb7)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb7 <- oddsratio(table_resatb7, conf.level = 0.95)$measure
# Print the formatted contingency table and test results
print(kable(table_resatb7, caption = "Contingency Table: Nationality vs. Perception of Bacteria Transmission Person to Person (RESATB7: True vs. False)"))
print(chi_result_resatb7)
print(odds_ratio_resatb7)

############ Verification using Fisher's test (in cases which one of the cells has 5 or less)
# Fisher's Exact Test for Count Data
fisher_result <- fisher.test(table_resatb7)
# Print the results of the Fisher's Exact Test
print(fisher_result)
# Calculating the odds ratio for a 2x2 table
# Note: Odds ratios can be calculated from Fisher test objects as well
odds_ratio <- fisher_result$estimate
# Calculating the confidence interval from the Fisher's Exact Test
confidence_interval <- fisher_result$conf.int
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

--------------------------------------------------------------------------------------------------------------------
  #####RESATB8	Antibiotic-resistant infections could make medical procedures like surgery, organ transplants,
  ##and cancer treatment much more dangerous (False=12.0%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
# Load the database
df <- Database_simplified
# Filter for 'True' and 'False' responses for RESATB8 and nationalities 'Canadian' and 'Other'
df_filtered_resatb8 <- df[df$RESATB8 %in% c(0, 1) & df$CIT1 %in% c(0, 1), ]
# Create the contingency table for 'True' vs 'False'
table_resatb8 <- table(df_filtered_resatb8$RESATB8, df_filtered_resatb8$CIT1)
# Add descriptive labels to rows and columns
rownames(table_resatb8) <- c("True", "False")
colnames(table_resatb8) <- c("Canadian", "Other")
# Perform the Chi-Squared test
chi_result_resatb8 <- chisq.test(table_resatb8)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb8 <- oddsratio(table_resatb8, conf.level = 0.95)$measure
# Print the formatted contingency table and test results
print(kable(table_resatb8, caption = "Contingency Table: Nationality vs. Perception of Antibiotic-Resistant Infections and Medical Procedures (RESATB8: True vs. False)"))
print(chi_result_resatb8)
print(odds_ratio_resatb8)

############ Verification using Fisher's test (in cases which one of the cells has 5 or less)
# Fisher's Exact Test for Count Data
fisher_result <- fisher.test(table_resatb8)
# Print the results of the Fisher's Exact Test
print(fisher_result)
# Calculating the odds ratio for a 2x2 table
# Note: Odds ratios can be calculated from Fisher test objects as well
odds_ratio <- fisher_result$estimate
# Calculating the confidence interval from the Fisher's Exact Test
confidence_interval <- fisher_result$conf.int
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

----------------------------------------------------------------------------------------------------
  
  # ATBRGL1	Farmers should give fewer antibiotics to food-producing animals 
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
# Load the database
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree for ATBRGL1
df_filtered_atbrgl1_scenario1 <- df[df$ATBRGL1 %in% c(1, 3) & df$CIT1 %in% c(0, 1), ]
table_atbrgl1_scenario1 <- table(df_filtered_atbrgl1_scenario1$ATBRGL1, df_filtered_atbrgl1_scenario1$CIT1)
rownames(table_atbrgl1_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl1_scenario1) <- c("Canadian", "Other")
chi_result_atbrgl1_scenario1 <- chisq.test(table_atbrgl1_scenario1)
odds_ratio_atbrgl1_scenario1 <- oddsratio(table_atbrgl1_scenario1, conf.level = 0.95)$measure
print(kable(table_atbrgl1_scenario1, caption = "Contingency Table: Nationality vs. ATBRGL1 (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl1_scenario1)
print(odds_ratio_atbrgl1_scenario1)

############ Verification using Fisher's test (in cases which one of the cells has 5 or less)
# Fisher's Exact Test for Count Data
fisher_result <- fisher.test(table_atbrgl1_scenario1)
# Print the results of the Fisher's Exact Test
print(fisher_result)
# Calculating the odds ratio for a 2x2 table
# Note: Odds ratios can be calculated from Fisher test objects as well
odds_ratio <- fisher_result$estimate
# Calculating the confidence interval from the Fisher's Exact Test
confidence_interval <- fisher_result$conf.int
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree for ATBRGL1
df_filtered_atbrgl1_scenario2 <- df[df$ATBRGL1 %in% c(2, 3) & df$CIT1 %in% c(0, 1), ]
table_atbrgl1_scenario2 <- table(df_filtered_atbrgl1_scenario2$ATBRGL1, df_filtered_atbrgl1_scenario2$CIT1)
rownames(table_atbrgl1_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl1_scenario2) <- c("Canadian", "Other")
chi_result_atbrgl1_scenario2 <- chisq.test(table_atbrgl1_scenario2)
odds_ratio_atbrgl1_scenario2 <- oddsratio(table_atbrgl1_scenario2, conf.level = 0.95)$measure
print(kable(table_atbrgl1_scenario2, caption = "Contingency Table: Nationality vs. ATBRGL1 (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl1_scenario2)
print(odds_ratio_atbrgl1_scenario2)


############################# 3rd scenario (Strongly desagree + Neither agree nor desagree=31.28%) vs. Strongly Agree
# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree for ATBRGL1
df_filtered_atbrgl1_scenario3 <- df[df$ATBRGL1 %in% c(1, 2, 3) & df$CIT1 %in% c(0, 1), ]
df_filtered_atbrgl1_scenario3$Disagree_Neither <- df_filtered_atbrgl1_scenario3$ATBRGL1 %in% c(1, 2)
table_atbrgl1_scenario3 <- table(df_filtered_atbrgl1_scenario3$Disagree_Neither, df_filtered_atbrgl1_scenario3$CIT1)
rownames(table_atbrgl1_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl1_scenario3) <- c("Canadian", "Other")
chi_result_atbrgl1_scenario3 <- chisq.test(table_atbrgl1_scenario3)
odds_ratio_atbrgl1_scenario3 <- oddsratio(table_atbrgl1_scenario3, conf.level = 0.95)$measure
print(kable(table_atbrgl1_scenario3, caption = "Contingency Table: Nationality vs. ATBRGL1 (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl1_scenario3)
print(odds_ratio_atbrgl1_scenario3)

--------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL2	People should not keep antibiotics and use them later for other illnesses  
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree for ATBRGL2
df_filtered_atbrgl2_scenario1 <- df[df$ATBRGL2 %in% c(1, 3) & df$CIT1 %in% c(0, 1), ]
table_atbrgl2_scenario1 <- table(df_filtered_atbrgl2_scenario1$ATBRGL2, df_filtered_atbrgl2_scenario1$CIT1)
rownames(table_atbrgl2_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl2_scenario1) <- c("Canadian", "Other")
chi_result_atbrgl2_scenario1 <- chisq.test(table_atbrgl2_scenario1)
odds_ratio_atbrgl2_scenario1 <- oddsratio(table_atbrgl2_scenario1, conf.level = 0.95)$measure
print(kable(table_atbrgl2_scenario1, caption = "Contingency Table: Nationality vs. ATBRGL2 (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl2_scenario1)
print(odds_ratio_atbrgl2_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree for ATBRGL2
df_filtered_atbrgl2_scenario2 <- df[df$ATBRGL2 %in% c(2, 3) & df$CIT1 %in% c(0, 1), ]
table_atbrgl2_scenario2 <- table(df_filtered_atbrgl2_scenario2$ATBRGL2, df_filtered_atbrgl2_scenario2$CIT1)
rownames(table_atbrgl2_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl2_scenario2) <- c("Canadian", "Other")
chi_result_atbrgl2_scenario2 <- chisq.test(table_atbrgl2_scenario2)
odds_ratio_atbrgl2_scenario2 <- oddsratio(table_atbrgl2_scenario2, conf.level = 0.95)$measure
print(kable(table_atbrgl2_scenario2, caption = "Contingency Table: Nationality vs. ATBRGL2 (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl2_scenario2)
print(odds_ratio_atbrgl2_scenario2)


# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree for ATBRGL2
df_filtered_atbrgl2_scenario3 <- df[df$ATBRGL2 %in% c(1, 2, 3) & df$CIT1 %in% c(0, 1), ]
df_filtered_atbrgl2_scenario3$Disagree_Neither <- df_filtered_atbrgl2_scenario3$ATBRGL2 %in% c(1, 2)
table_atbrgl2_scenario3 <- table(df_filtered_atbrgl2_scenario3$Disagree_Neither, df_filtered_atbrgl2_scenario3$CIT1)
rownames(table_atbrgl2_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl2_scenario3) <- c("Canadian", "Other")
chi_result_atbrgl2_scenario3 <- chisq.test(table_atbrgl2_scenario3)
odds_ratio_atbrgl2_scenario3 <- oddsratio(table_atbrgl2_scenario3, conf.level = 0.95)$measure
print(kable(table_atbrgl2_scenario3, caption = "Contingency Table: Nationality vs. ATBRGL2 (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl2_scenario3)
print(odds_ratio_atbrgl2_scenario3)


--------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL3 Parents should make sure all of their children’s vaccinations are up-to-date 
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree for ATBRGL3
df_filtered_atbrgl3_scenario1 <- df[df$ATBRGL3 %in% c(1, 3) & df$CIT1 %in% c(0, 1), ]
table_atbrgl3_scenario1 <- table(df_filtered_atbrgl3_scenario1$ATBRGL3, df_filtered_atbrgl3_scenario1$CIT1)
rownames(table_atbrgl3_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl3_scenario1) <- c("Canadian", "Other")
chi_result_atbrgl3_scenario1 <- chisq.test(table_atbrgl3_scenario1)
odds_ratio_atbrgl3_scenario1 <- oddsratio(table_atbrgl3_scenario1, conf.level = 0.95)$measure
print(kable(table_atbrgl3_scenario1, caption = "Contingency Table: Nationality vs. ATBRGL3 (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl3_scenario1)
print(odds_ratio_atbrgl3_scenario1)


# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree for ATBRGL3
df_filtered_atbrgl3_scenario2 <- df[df$ATBRGL3 %in% c(2, 3) & df$CIT1 %in% c(0, 1), ]
table_atbrgl3_scenario2 <- table(df_filtered_atbrgl3_scenario2$ATBRGL3, df_filtered_atbrgl3_scenario2$CIT1)
rownames(table_atbrgl3_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl3_scenario2) <- c("Canadian", "Other")
chi_result_atbrgl3_scenario2 <- chisq.test(table_atbrgl3_scenario2)
odds_ratio_atbrgl3_scenario2 <- oddsratio(table_atbrgl3_scenario2, conf.level = 0.95)$measure
print(kable(table_atbrgl3_scenario2, caption = "Contingency Table: Nationality vs. ATBRGL3 (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl3_scenario2)
print(odds_ratio_atbrgl3_scenario2)

# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree for ATBRGL3
df_filtered_atbrgl3_scenario3 <- df[df$ATBRGL3 %in% c(1, 2, 3) & df$CIT1 %in% c(0, 1), ]
df_filtered_atbrgl3_scenario3$Disagree_Neither <- df_filtered_atbrgl3_scenario3$ATBRGL3 %in% c(1, 2)
table_atbrgl3_scenario3 <- table(df_filtered_atbrgl3_scenario3$Disagree_Neither, df_filtered_atbrgl3_scenario3$CIT1)
rownames(table_atbrgl3_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl3_scenario3) <- c("Canadian", "Other")
chi_result_atbrgl3_scenario3 <- chisq.test(table_atbrgl3_scenario3)
odds_ratio_atbrgl3_scenario3 <- oddsratio(table_atbrgl3_scenario3, conf.level = 0.95)$measure
print(kable(table_atbrgl3_scenario3, caption = "Contingency Table: Nationality vs. ATBRGL3 (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl3_scenario3)
print(odds_ratio_atbrgl3_scenario3)

---------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL4 People should wash their hands regularly
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree for ATBRGL4
df_filtered_atbrgl4_scenario1 <- df[df$ATBRGL4 %in% c(1, 3) & df$CIT1 %in% c(0, 1), ]
table_atbrgl4_scenario1 <- table(df_filtered_atbrgl4_scenario1$ATBRGL4, df_filtered_atbrgl4_scenario1$CIT1)
rownames(table_atbrgl4_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl4_scenario1) <- c("Canadian", "Other")
chi_result_atbrgl4_scenario1 <- chisq.test(table_atbrgl4_scenario1)
odds_ratio_atbrgl4_scenario1 <- oddsratio(table_atbrgl4_scenario1, conf.level = 0.95)$measure
print(kable(table_atbrgl4_scenario1, caption = "Contingency Table: Nationality vs. ATBRGL4 (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl4_scenario1)
print(odds_ratio_atbrgl4_scenario1)

############ Verification using Fisher's test (in cases which one of the cells has 5 or less)
# Fisher's Exact Test for Count Data
fisher_result <- fisher.test(table_atbrgl4_scenario1)
# Print the results of the Fisher's Exact Test
print(fisher_result)
# Calculating the odds ratio for a 2x2 table
# Note: Odds ratios can be calculated from Fisher test objects as well
odds_ratio <- fisher_result$estimate
# Calculating the confidence interval from the Fisher's Exact Test
confidence_interval <- fisher_result$conf.int
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree para ATBRGL4
df_filtered_atbrgl4_scenario2 <- df[df$ATBRGL4 %in% c(2, 3) & df$CIT1 %in% c(0, 1), ]
table_atbrgl4_scenario2 <- table(df_filtered_atbrgl4_scenario2$ATBRGL4, df_filtered_atbrgl4_scenario2$CIT1)
rownames(table_atbrgl4_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl4_scenario2) <- c("Canadian", "Other")
chi_result_atbrgl4_scenario2 <- chisq.test(table_atbrgl4_scenario2)
odds_ratio_atbrgl4_scenario2 <- oddsratio(table_atbrgl4_scenario2, conf.level = 0.95)$measure
print(kable(table_atbrgl4_scenario2, caption = "Contingency Table: Nationality vs. ATBRGL4 (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl4_scenario2)
print(odds_ratio_atbrgl4_scenario2)

# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree for ATBRGL4
df_filtered_atbrgl4_scenario3 <- df[df$ATBRGL4 %in% c(1, 2, 3) & df$CIT1 %in% c(0, 1), ]
df_filtered_atbrgl4_scenario3$Disagree_Neither <- df_filtered_atbrgl4_scenario3$ATBRGL4 %in% c(1, 2)
table_atbrgl4_scenario3 <- table(df_filtered_atbrgl4_scenario3$Disagree_Neither, df_filtered_atbrgl4_scenario3$CIT1)
rownames(table_atbrgl4_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl4_scenario3) <- c("Canadian", "Other")
chi_result_atbrgl4_scenario3 <- chisq.test(table_atbrgl4_scenario3)
odds_ratio_atbrgl4_scenario3 <- oddsratio(table_atbrgl4_scenario3, conf.level = 0.95)$measure
print(kable(table_atbrgl4_scenario3, caption = "Contingency Table: Nationality vs. ATBRGL4 (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl4_scenario3)
print(odds_ratio_atbrgl4_scenario3)


---------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL5 Doctors should only prescribe antibiotics when they are needed 
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
# Load the Database_simplified dataframe
df <- Database_simplified

## Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_atbrgl5_scenario1 <- df[df$ATBRGL5 %in% c(1, 3) & df$CIT1 %in% c(0, 1), ]
table_atbrgl5_scenario1 <- table(df_filtered_atbrgl5_scenario1$ATBRGL5, df_filtered_atbrgl5_scenario1$CIT1)
rownames(table_atbrgl5_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl5_scenario1) <- c("Canadian", "Other")
chi_result_atbrgl5_scenario1 <- chisq.test(table_atbrgl5_scenario1)
odds_ratio_atbrgl5_scenario1 <- oddsratio(table_atbrgl5_scenario1, conf.level = 0.95)$measure
print(kable(table_atbrgl5_scenario1, caption = "Contingency Table: Nationality vs. ATBRGL5 (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl5_scenario1)
print(odds_ratio_atbrgl5_scenario1)

############ Verification using Fisher's test (in cases which one of the cells has 5 or less)
# Fisher's Exact Test for Count Data
fisher_result <- fisher.test(table_atbrgl5_scenario1)
# Print the results of the Fisher's Exact Test
print(fisher_result)
# Calculating the odds ratio for a 2x2 table
# Note: Odds ratios can be calculated from Fisher test objects as well
odds_ratio <- fisher_result$estimate
# Calculating the confidence interval from the Fisher's Exact Test
confidence_interval <- fisher_result$conf.int
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)


## Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl5_scenario2 <- df[df$ATBRGL5 %in% c(2, 3) & df$CIT1 %in% c(0, 1), ]
table_atbrgl5_scenario2 <- table(df_filtered_atbrgl5_scenario2$ATBRGL5, df_filtered_atbrgl5_scenario2$CIT1)
rownames(table_atbrgl5_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl5_scenario2) <- c("Canadian", "Other")
chi_result_atbrgl5_scenario2 <- chisq.test(table_atbrgl5_scenario2)
odds_ratio_atbrgl5_scenario2 <- oddsratio(table_atbrgl5_scenario2, conf.level = 0.95)$measure
print(kable(table_atbrgl5_scenario2, caption = "Contingency Table: Nationality vs. ATBRGL5 (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl5_scenario2)
print(odds_ratio_atbrgl5_scenario2)

############ Verification using Fisher's test (in cases which one of the cells has 5 or less)
# Fisher's Exact Test for Count Data
fisher_result <- fisher.test(table_atbrgl5_scenario2)
# Print the results of the Fisher's Exact Test
print(fisher_result)
# Calculating the odds ratio for a 2x2 table
# Note: Odds ratios can be calculated from Fisher test objects as well
odds_ratio <- fisher_result$estimate
# Calculating the confidence interval from the Fisher's Exact Test
confidence_interval <- fisher_result$conf.int
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)


## Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl5_scenario3 <- df[df$ATBRGL5 %in% c(1, 2, 3) & df$CIT1 %in% c(0, 1), ]
df_filtered_atbrgl5_scenario3$Disagree_Neither <- df_filtered_atbrgl5_scenario3$ATBRGL5 %in% c(1, 2)
table_atbrgl5_scenario3 <- table(df_filtered_atbrgl5_scenario3$Disagree_Neither, df_filtered_atbrgl5_scenario3$CIT1)
rownames(table_atbrgl5_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl5_scenario3) <- c("Canadian", "Other")
chi_result_atbrgl5_scenario3 <- chisq.test(table_atbrgl5_scenario3)
odds_ratio_atbrgl5_scenario3 <- oddsratio(table_atbrgl5_scenario3, conf.level = 0.95)$measure
print(kable(table_atbrgl5_scenario3, caption = "Contingency Table: Nationality vs. ATBRGL5 (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl5_scenario3)
print(odds_ratio_atbrgl5_scenario3)

############ Verification using Fisher's test (in cases which one of the cells has 5 or less)
# Fisher's Exact Test for Count Data
fisher_result <- fisher.test(table_atbrgl5_scenario3)
# Print the results of the Fisher's Exact Test
print(fisher_result)
# Calculating the odds ratio for a 2x2 table
# Note: Odds ratios can be calculated from Fisher test objects as well
odds_ratio <- fisher_result$estimate
# Calculating the confidence interval from the Fisher's Exact Test
confidence_interval <- fisher_result$conf.int
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)


----------------------------------------------------------------------------------------------------------------------
  
  ##ATBRGL6= People should only use antibiotics when prescribed by a doctor or nurse
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

## Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_atbrgl6_scenario1 <- df[df$ATBRGL6 %in% c(1, 3) & df$CIT1 %in% c(0, 1), ]
table_atbrgl6_scenario1 <- table(df_filtered_atbrgl6_scenario1$ATBRGL6, df_filtered_atbrgl6_scenario1$CIT1)
rownames(table_atbrgl6_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl6_scenario1) <- c("Canadian", "Other")
chi_result_atbrgl6_scenario1 <- chisq.test(table_atbrgl6_scenario1)
odds_ratio_atbrgl6_scenario1 <- oddsratio(table_atbrgl6_scenario1, conf.level = 0.95)$measure
print(kable(table_atbrgl6_scenario1, caption = "Contingency Table: Nationality vs. ATBRGL6 (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl6_scenario1)
print(odds_ratio_atbrgl6_scenario1)

############ Verification using Fisher's test (in cases which one of the cells has 5 or less)
# Fisher's Exact Test for Count Data
fisher_result <- fisher.test(table_atbrgl6_scenario1)
# Print the results of the Fisher's Exact Test
print(fisher_result)
# Calculating the odds ratio for a 2x2 table
# Note: Odds ratios can be calculated from Fisher test objects as well
odds_ratio <- fisher_result$estimate
# Calculating the confidence interval from the Fisher's Exact Test
confidence_interval <- fisher_result$conf.int
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)


## Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl6_scenario2 <- df[df$ATBRGL6 %in% c(2, 3) & df$CIT1 %in% c(0, 1), ]
table_atbrgl6_scenario2 <- table(df_filtered_atbrgl6_scenario2$ATBRGL6, df_filtered_atbrgl6_scenario2$CIT1)
rownames(table_atbrgl6_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl6_scenario2) <- c("Canadian", "Other")
chi_result_atbrgl6_scenario2 <- chisq.test(table_atbrgl6_scenario2)
odds_ratio_atbrgl6_scenario2 <- oddsratio(table_atbrgl6_scenario2, conf.level = 0.95)$measure
print(kable(table_atbrgl6_scenario2, caption = "Contingency Table: Nationality vs. ATBRGL6 (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl6_scenario2)
print(odds_ratio_atbrgl6_scenario2)

############ Verification using Fisher's test (in cases which one of the cells has 5 or less)
# Fisher's Exact Test for Count Data
fisher_result <- fisher.test(table_atbrgl6_scenario2)
# Print the results of the Fisher's Exact Test
print(fisher_result)
# Calculating the odds ratio for a 2x2 table
# Note: Odds ratios can be calculated from Fisher test objects as well
odds_ratio <- fisher_result$estimate
# Calculating the confidence interval from the Fisher's Exact Test
confidence_interval <- fisher_result$conf.int
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)


## Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl6_scenario3 <- df[df$ATBRGL6 %in% c(1, 2, 3) & df$CIT1 %in% c(0, 1), ]
df_filtered_atbrgl6_scenario3$Disagree_Neither <- df_filtered_atbrgl6_scenario3$ATBRGL6 %in% c(1, 2)
table_atbrgl6_scenario3 <- table(df_filtered_atbrgl6_scenario3$Disagree_Neither, df_filtered_atbrgl6_scenario3$CIT1)
rownames(table_atbrgl6_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl6_scenario3) <- c("Canadian", "Other")
chi_result_atbrgl6_scenario3 <- chisq.test(table_atbrgl6_scenario3)
odds_ratio_atbrgl6_scenario3 <- oddsratio(table_atbrgl6_scenario3, conf.level = 0.95)$measure
print(kable(table_atbrgl6_scenario3, caption = "Contingency Table: Nationality vs. ATBRGL6 (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl6_scenario3)
print(odds_ratio_atbrgl6_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM1= Antibiotic resistance is one of the biggest problems the world faces
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Load the Database_simplified dataframe
df <- read_excel("C:/Database_simplified.xlsx")

# Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_resdim1_scenario1 <- df[df$RESDIM1 %in% c(1, 3) & df$CIT1 %in% c(0, 1), ]
table_resdim1_scenario1 <- table(df_filtered_resdim1_scenario1$RESDIM1, df_filtered_resdim1_scenario1$CIT1)
rownames(table_resdim1_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim1_scenario1) <- c("Canadian", "Other")
chi_result_resdim1_scenario1 <- chisq.test(table_resdim1_scenario1)
odds_ratio_resdim1_scenario1 <- oddsratio(table_resdim1_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim1_scenario1, caption = "Contingency Table: Nationality vs. Perception of Antibiotic Resistance as a Global Problem (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_resdim1_scenario1)
print(odds_ratio_resdim1_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim1_scenario2 <- df[df$RESDIM1 %in% c(2, 3) & df$CIT1 %in% c(0, 1), ]
table_resdim1_scenario2 <- table(df_filtered_resdim1_scenario2$RESDIM1, df_filtered_resdim1_scenario2$CIT1)
rownames(table_resdim1_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_resdim1_scenario2) <- c("Canadian", "Other")
chi_result_resdim1_scenario2 <- chisq.test(table_resdim1_scenario2)
odds_ratio_resdim1_scenario2 <- oddsratio(table_resdim1_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim1_scenario2, caption = "Contingency Table: Nationality vs. Perception of Antibiotic Resistance as a Global Problem (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim1_scenario2)
print(odds_ratio_resdim1_scenario2)

# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim1_scenario3 <- df[df$RESDIM1 %in% c(1, 2, 3) & df$CIT1 %in% c(0, 1), ]
df_filtered_resdim1_scenario3$Disagree_Neither <- df_filtered_resdim1_scenario3$RESDIM1 %in% c(1, 2)
table_resdim1_scenario3 <- table(df_filtered_resdim1_scenario3$Disagree_Neither, df_filtered_resdim1_scenario3$CIT1)
rownames(table_resdim1_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_resdim1_scenario3) <- c("Canadian", "Other")
chi_result_resdim1_scenario3 <- chisq.test(table_resdim1_scenario3)
odds_ratio_resdim1_scenario3 <- oddsratio(table_resdim1_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim1_scenario3, caption = "Contingency Table: Nationality vs. Perception of Antibiotic Resistance as a Global Problem (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_resdim1_scenario3)
print(odds_ratio_resdim1_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM2= Medical experts will solve the problem of antibiotic resistance before it becomes too serious 
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Load the Database_simplified dataframe
df <- read_excel("C:/Database_simplified.xlsx")

# Scenario 1: Strongly Agree vs. Strongly Disagree
df_filtered_resdim2_scenario1 <- df[df$RESDIM2 %in% c(1, 3) & df$CIT1 %in% c(0, 1), ]
table_resdim2_scenario1 <- table(df_filtered_resdim2_scenario1$RESDIM2, df_filtered_resdim2_scenario1$CIT1)
rownames(table_resdim2_scenario1) <- c("Strongly Agree", "Strongly Disagree")
colnames(table_resdim2_scenario1) <- c("Canadian", "Other")
chi_result_resdim2_scenario1 <- chisq.test(table_resdim2_scenario1)
odds_ratio_resdim2_scenario1 <- oddsratio(table_resdim2_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim2_scenario1, caption = "Contingency Table: Nationality vs. Belief in Solving Antibiotic Resistance (Strongly Disagree vs. Strongly Agree)"))
print(chi_result_resdim2_scenario1)
print(odds_ratio_resdim2_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim2_scenario2 <- df[df$RESDIM2 %in% c(1, 2) & df$CIT1 %in% c(0, 1), ]
table_resdim2_scenario2 <- table(df_filtered_resdim2_scenario2$RESDIM2, df_filtered_resdim2_scenario2$CIT1)
rownames(table_resdim2_scenario2) <- c("Strongly Disagree", "Neither Agree Nor Disagree")
colnames(table_resdim2_scenario2) <- c("Canadian", "Other")
chi_result_resdim2_scenario2 <- chisq.test(table_resdim2_scenario2)
odds_ratio_resdim2_scenario2 <- oddsratio(table_resdim2_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim2_scenario2, caption = "Contingency Table: Nationality vs. Belief in Solving Antibiotic Resistance (Strongly Disagree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim2_scenario2)
print(odds_ratio_resdim2_scenario2)

# Scenario 3: Strongly Agree + Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim2_scenario3 <- df[df$RESDIM2 %in% c(1, 2, 3) & df$CIT1 %in% c(0, 1), ]
df_filtered_resdim2_scenario3$Agree_Neither <- df_filtered_resdim2_scenario3$RESDIM2 %in% c(2, 3)
table_resdim2_scenario3 <- table(df_filtered_resdim2_scenario3$Agree_Neither, df_filtered_resdim2_scenario3$CIT1)
rownames(table_resdim2_scenario3) <- c("Strongly Disagree", "Strongly Agree + Neither")
colnames(table_resdim2_scenario3) <- c("Canadian", "Other")
chi_result_resdim2_scenario3 <- chisq.test(table_resdim2_scenario3)
odds_ratio_resdim2_scenario3 <- oddsratio(table_resdim2_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim2_scenario3, caption = "Contingency Table: Nationality vs. Belief in Solving Antibiotic Resistance (Strongly Disagree vs. Strongly Agree + Neither Agree Nor Disagree)"))
print(chi_result_resdim2_scenario3)
print(odds_ratio_resdim2_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM3= Everyone needs to use antibiotics responsibly
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_resdim3_scenario1 <- df[df$RESDIM3 %in% c(1, 3) & df$CIT1 %in% c(0, 1), ]
table_resdim3_scenario1 <- table(df_filtered_resdim3_scenario1$RESDIM3, df_filtered_resdim3_scenario1$CIT1)
rownames(table_resdim3_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim3_scenario1) <- c("Canadian", "Other")
chi_result_resdim3_scenario1 <- chisq.test(table_resdim3_scenario1)
odds_ratio_resdim3_scenario1 <- oddsratio(table_resdim3_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim3_scenario1, caption = "Contingency Table: Nationality vs. Everyone Needs to Use Antibiotics Responsibly (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_resdim3_scenario1)
print(odds_ratio_resdim3_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim3_scenario2 <- df[df$RESDIM3 %in% c(2, 3) & df$CIT1 %in% c(0, 1), ]
table_resdim3_scenario2 <- table(df_filtered_resdim3_scenario2$RESDIM3, df_filtered_resdim3_scenario2$CIT1)
rownames(table_resdim3_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_resdim3_scenario2) <- c("Canadian", "Other")
chi_result_resdim3_scenario2 <- chisq.test(table_resdim3_scenario2)
odds_ratio_resdim3_scenario2 <- oddsratio(table_resdim3_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim3_scenario2, caption = "Contingency Table: Nationality vs. Everyone Needs to Use Antibiotics Responsibly (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim3_scenario2)
print(odds_ratio_resdim3_scenario2)

# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim3_scenario3 <- df[df$RESDIM3 %in% c(1, 2, 3) & df$CIT1 %in% c(0, 1), ]
df_filtered_resdim3_scenario3$Disagree_Neither <- df_filtered_resdim3_scenario3$RESDIM3 %in% c(1, 2)
table_resdim3_scenario3 <- table(df_filtered_resdim3_scenario3$Disagree_Neither, df_filtered_resdim3_scenario3$CIT1)
rownames(table_resdim3_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_resdim3_scenario3) <- c("Canadian", "Other")
chi_result_resdim3_scenario3 <- chisq.test(table_resdim3_scenario3)
odds_ratio_resdim3_scenario3 <- oddsratio(table_resdim3_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim3_scenario3, caption = "Contingency Table: Nationality vs. Everyone Needs to Use Antibiotics Responsibly (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_resdim3_scenario3)
print(odds_ratio_resdim3_scenario3)

----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM4= People like me can't do much to stop antibiotic resistance
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified


# Scenario 1: Strongly Agree vs. Strongly Disagree
df_filtered_resdim4_scenario1 <- df[df$RESDIM4 %in% c(1, 3) & df$CIT1 %in% c(0, 1), ]
table_resdim4_scenario1 <- table(df_filtered_resdim4_scenario1$RESDIM4, df_filtered_resdim4_scenario1$CIT1)
rownames(table_resdim4_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim4_scenario1) <- c("Canadian", "Other")
chi_result_resdim4_scenario1 <- chisq.test(table_resdim4_scenario1)
odds_ratio_resdim4_scenario1 <- oddsratio(table_resdim4_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim4_scenario1, caption = "Contingency Table: Nationality vs. Belief in Individual Impact on Antibiotic Resistance (Strongly Disagree vs. Strongly Agree)"))
print(chi_result_resdim4_scenario1)
print(odds_ratio_resdim4_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim4_scenario2 <- df[df$RESDIM4 %in% c(1, 2) & df$CIT1 %in% c(0, 1), ]
table_resdim4_scenario2 <- table(df_filtered_resdim4_scenario2$RESDIM4, df_filtered_resdim4_scenario2$CIT1)
rownames(table_resdim4_scenario2) <- c("Strongly Disagree", "Neither Agree Nor Disagree")
colnames(table_resdim4_scenario2) <- c("Canadian", "Other")
chi_result_resdim4_scenario2 <- chisq.test(table_resdim4_scenario2)
odds_ratio_resdim4_scenario2 <- oddsratio(table_resdim4_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim4_scenario2, caption = "Contingency Table: Nationality vs. Belief in Individual Impact on Antibiotic Resistance (Strongly Disagree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim4_scenario2)
print(odds_ratio_resdim4_scenario2)

# Scenario 3: Strongly Agree + Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim4_scenario3 <- df[df$RESDIM4 %in% c(1, 2, 3) & df$CIT1 %in% c(0, 1), ]
df_filtered_resdim4_scenario3$Agree_Neither <- df_filtered_resdim4_scenario3$RESDIM4 %in% c(2, 3)
table_resdim4_scenario3 <- table(df_filtered_resdim4_scenario3$Agree_Neither, df_filtered_resdim4_scenario3$CIT1)
rownames(table_resdim4_scenario3) <- c("Strongly Disagree", "Strongly Agree + Neither")
colnames(table_resdim4_scenario3) <- c("Canadian", "Other")
chi_result_resdim4_scenario3 <- chisq.test(table_resdim4_scenario3)
odds_ratio_resdim4_scenario3 <- oddsratio(table_resdim4_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim4_scenario3, caption = "Contingency Table: Nationality vs. Belief in Individual Impact on Antibiotic Resistance (Strongly Disagree vs. Strongly Agree + Neither Agree Nor Disagree)"))
print(chi_result_resdim4_scenario3)
print(odds_ratio_resdim4_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM5= I am worried about the impact that antibiotic resistance will have on my health and that of my family
  
  # Load the Database_simplified dataframe
  df <- read_excel("C:/Database_simplified.xlsx")

# Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_resdim5_scenario1 <- df[df$RESDIM5 %in% c(1, 3) & df$CIT1 %in% c(0, 1), ]
table_resdim5_scenario1 <- table(df_filtered_resdim5_scenario1$RESDIM5, df_filtered_resdim5_scenario1$CIT1)
rownames(table_resdim5_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim5_scenario1) <- c("Canadian", "Other")
chi_result_resdim5_scenario1 <- chisq.test(table_resdim5_scenario1)
odds_ratio_resdim5_scenario1 <- oddsratio(table_resdim5_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim5_scenario1, caption = "Contingency Table: Nationality vs. Impact of AMR on personal health and that of their family (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_resdim5_scenario1)
print(odds_ratio_resdim5_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim5_scenario2 <- df[df$RESDIM5 %in% c(2, 3) & df$CIT1 %in% c(0, 1), ]
table_resdim5_scenario2 <- table(df_filtered_resdim5_scenario2$RESDIM5, df_filtered_resdim5_scenario2$CIT1)
rownames(table_resdim5_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_resdim5_scenario2) <- c("Canadian", "Other")
chi_result_resdim5_scenario2 <- chisq.test(table_resdim5_scenario2)
odds_ratio_resdim5_scenario2 <- oddsratio(table_resdim5_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim5_scenario2, caption = "Contingency Table: Nationality vs. Impact of AMR on personal health and that of their family (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim5_scenario2)
print(odds_ratio_resdim5_scenario2)

# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim5_scenario3 <- df[df$RESDIM5 %in% c(1, 2, 3) & df$CIT1 %in% c(0, 1), ]
df_filtered_resdim5_scenario3$Disagree_Neither <- df_filtered_resdim5_scenario3$RESDIM5 %in% c(1, 2)
table_resdim5_scenario3 <- table(df_filtered_resdim5_scenario3$Disagree_Neither, df_filtered_resdim5_scenario3$CIT1)
rownames(table_resdim5_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_resdim5_scenario3) <- c("Canadian", "Other")
chi_result_resdim5_scenario3 <- chisq.test(table_resdim5_scenario3)
odds_ratio_resdim5_scenario3 <- oddsratio(table_resdim5_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim5_scenario3, caption = "Contingency Table: Nationality vs. Impact of AMR on personal health and that of their family (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_resdim5_scenario3)
print(odds_ratio_resdim5_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM6= I am not at risk of getting an antibiotic-resistant infection, as long as I take my antibiotics correctly
  
  # Load the Database_simplified dataframe
  df <- read_excel("C:/Database_simplified.xlsx")

# Scenario 1: Strongly Agree vs. Strongly Disagree
df_filtered_resdim6_scenario1 <- df[df$RESDIM6 %in% c(1, 3) & df$CIT1 %in% c(0, 1), ]
table_resdim6_scenario1 <- table(df_filtered_resdim6_scenario1$RESDIM6, df_filtered_resdim6_scenario1$CIT1)
rownames(table_resdim6_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim6_scenario1) <- c("Canadian", "Other")
chi_result_resdim6_scenario1 <- chisq.test(table_resdim6_scenario1)
odds_ratio_resdim6_scenario1 <- oddsratio(table_resdim6_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim6_scenario1, caption = "Contingency Table: Nationality vs. Perception of Risk of Antibiotic-Resistant Infection (Strongly Disagree vs. Strongly Agree)"))
print(chi_result_resdim6_scenario1)
print(odds_ratio_resdim6_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim6_scenario2 <- df[df$RESDIM6 %in% c(1, 2) & df$CIT1 %in% c(0, 1), ]
table_resdim6_scenario2 <- table(df_filtered_resdim6_scenario2$RESDIM6, df_filtered_resdim6_scenario2$CIT1)
rownames(table_resdim6_scenario2) <- c("Strongly Disagree", "Neither Agree Nor Disagree")
colnames(table_resdim6_scenario2) <- c("Canadian", "Other")
chi_result_resdim6_scenario2 <- chisq.test(table_resdim6_scenario2)
odds_ratio_resdim6_scenario2 <- oddsratio(table_resdim6_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim6_scenario2, caption = "Contingency Table: Nationality vs. Perception of Risk of Antibiotic-Resistant Infection (Strongly Disagree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim6_scenario2)
print(odds_ratio_resdim6_scenario2)

# Scenario 3: Strongly Agree + Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim6_scenario3 <- df[df$RESDIM6 %in% c(1, 2, 3) & df$CIT1 %in% c(0, 1), ]
df_filtered_resdim6_scenario3$Agree_Neither <- df_filtered_resdim6_scenario3$RESDIM6 %in% c(2, 3)
table_resdim6_scenario3 <- table(df_filtered_resdim6_scenario3$Agree_Neither, df_filtered_resdim6_scenario3$CIT1)
rownames(table_resdim6_scenario3) <- c("Strongly Disagree", "Strongly Agree + Neither")
colnames(table_resdim6_scenario3) <- c("Canadian", "Other")
chi_result_resdim6_scenario3 <- chisq.test(table_resdim6_scenario3)
odds_ratio_resdim6_scenario3 <- oddsratio(table_resdim6_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim6_scenario3, caption = "Contingency Table: Nationality vs. Perception of Risk of Antibiotic-Resistant Infection (Strongly Disagree vs. Strongly Agree + Neither Agree Nor Disagree)"))
print(chi_result_resdim6_scenario3)
print(odds_ratio_resdim6_scenario3)

############################################### Comparisons by Age#############################################
###############################################  18-34 vs. Other ###############################################

###CUSIN1 (I wash my hands before cooking (No= 9.4%))

# Load the Database_simplified dataframe
Database_simplified <- read_excel("C:/Database_simplified.xlsx")

# Filter the DataFrame
df_filtered <- Database_simplified[Database_simplified$CUSIN1 %in% c(0, 1) & Database_simplified$AGE %in% c(1, 2, 3, 4, 5, 6), ]

# Create a new variable for age categorization
df_filtered$Age_Group <- ifelse(df_filtered$AGE %in% c(1, 2), "18-34", "35+")

# Create the Contingency Table
table <- table(df_filtered$CUSIN1, df_filtered$Age_Group)

# Add descriptive labels
rownames(table) <- c("CUSIN1 (Yes)", "CUSIN1 (No)")
colnames(table) <- c("18-34", "35+")

# Print the contingency table using knitr
kable(table, caption = "Contingency Table: Age Group vs. Hand Washing")

# Chi-Square Test
chi_result <- chisq.test(table)

# Print the results of the Chi-Square Test
print(chi_result)

# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])

# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure

# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

---------------------------------------------------------------------------------------------------
  
  ##CUSIN2 (After handling raw food (meat and vegetables), I wash my hands with soap (No= 15.1%)
  
  df_filtered <- Database_simplified[Database_simplified$CUSIN2 %in% c(0, 1) & Database_simplified$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered$Age_Group <- ifelse(df_filtered$AGE %in% c(1, 2), "18-34", "35+")
table <- table(df_filtered$CUSIN2, df_filtered$Age_Group)
rownames(table) <- c("CUSIN2 (Yes)", "CUSIN2 (No)")
colnames(table) <- c("18-34", "35+")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: AGE vs. After handling raw food (meat and vegetables), I wash my hands with soap")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN3 (I use the same kitchen utensils for handling raw and ready-to-eat foods (Yes=25.8%))
  
  df_filtered <- Database_simplified[Database_simplified$CUSIN3 %in% c(0, 1) & Database_simplified$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered$Age_Group <- ifelse(df_filtered$AGE %in% c(1, 2), "18-34", "35+")
table <- table(df_filtered$CUSIN3, df_filtered$Age_Group)
rownames(table) <- c("CUSIN3 (Yes)", "CUSIN3 (No)")
colnames(table) <- c("18-34", "35+")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: AGE vs. I use the same kitchen utensils for handling raw and ready-to-eat foods")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

-------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN4 (I wash kitchen utensils that have been used for raw food before using them to prepare other foods  (No=16.8%))
  
  df_filtered <- Database_simplified[Database_simplified$CUSIN4 %in% c(0, 1) & Database_simplified$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered$Age_Group <- ifelse(df_filtered$AGE %in% c(1, 2), "18-34", "35+")
table <- table(df_filtered$CUSIN4, df_filtered$Age_Group)
rownames(table) <- c("CUSIN4 (Yes)", "CUSIN4 (No)")
colnames(table) <- c("18-34", "35+")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Age vs. I wash kitchen utensils that have been used for raw food before using them to prepare other foods")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

-------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN5 (I wash fruits and vegetables before eating them (No=20.7%))
  
  df_filtered <- Database_simplified[Database_simplified$CUSIN5 %in% c(0, 1) & Database_simplified$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered$Age_Group <- ifelse(df_filtered$AGE %in% c(1, 2), "18-34", "35+")
table <- table(df_filtered$CUSIN5, df_filtered$Age_Group)
rownames(table) <- c("CUSIN5 (Yes)", "CUSIN5 (No)")
colnames(table) <- c("18-34", "35+")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Age vs. I wash fruits and vegetables before eating them")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

-------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN6 (I wash my hands before eating (No=21.5))
  
  df_filtered <- Database_simplified[Database_simplified$CUSIN6 %in% c(0, 1) & Database_simplified$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered$Age_Group <- ifelse(df_filtered$AGE %in% c(1, 2), "18-34", "35+")
table <- table(df_filtered$CUSIN6, df_filtered$Age_Group)
rownames(table) <- c("CUSIN6 (Yes)", "CUSIN6 (No)")
colnames(table) <- c("18-34", "35+")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Age vs. I wash my hands before eating")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

---------------------------------------------------------------------------------------------------------------------
  
  ##PRESCATB1 When you get a prescription for antibiotics, do you follow the recommended 
  ##length of treatment and daily dosage? (No=4.2%) (Sometimes=9.6%) (No+Sometimes=13.8%)
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
df <- Database_simplified
############### 1st scenario= No
df_filtered_prescatb1 <- df[df$PRESCATB1 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_prescatb1$Age_Group <- ifelse(df_filtered_prescatb1$AGE %in% c(1, 2), "18-34", "35+")
table_prescatb1 <- table(df_filtered_prescatb1$PRESCATB1, df_filtered_prescatb1$Age_Group)
# Add descriptive labels to the rows and columns
rownames(table_prescatb1) <- c("Yes", "No")
# Perform the Chi-Squared test
chi_result_prescatb1 <- chisq.test(table_prescatb1)
# Calculate the odds ratio and confidence interval
odds_ratio_prescatb1 <- oddsratio(table_prescatb1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_prescatb1, caption = "Contingency Table: Age vs. Following Prescription for Antibiotics"))
# Print the results of the Chi-Squared test
print(chi_result_prescatb1)
# Print the odds ratio and confidence interval
print(odds_ratio_prescatb1)

################## 2nd scenario= Sometimes
df_filtered_prescatb1_sometimes <- df[df$PRESCATB1 %in% c(0, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_prescatb1_sometimes$Age_Group <- ifelse(df_filtered_prescatb1_sometimes$AGE %in% c(1, 2), "18-34", "35+")
table_prescatb1_sometimes <- table(df_filtered_prescatb1_sometimes$PRESCATB1, df_filtered_prescatb1_sometimes$Age_Group)
# Add descriptive labels to the rows and columns
rownames(table_prescatb1_sometimes) <- c("Yes", "No")
# Perform the Chi-Squared test
chi_result_prescatb1_sometimes <- chisq.test(table_prescatb1_sometimes)
# Calculate the odds ratio and confidence interval
odds_ratio_prescatb1_sometimes <- oddsratio(table_prescatb1_sometimes, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_prescatb1_sometimes, caption = "Contingency Table: Age vs. Following Prescription for Antibiotics Sometimes"))
# Print the results of the Chi-Squared test
print(chi_result_prescatb1_sometimes)
# Print the odds ratio and confidence interval
print(odds_ratio_prescatb1_sometimes)

################## 3rd scenario= No+Sometimes
# Filter for 'Yes', 'No', and 'Sometimes' responses for PRESCATB1 and genders 'Female' and 'Male'
df_filtered_prescatb1_combined <- df[df$PRESCATB1 %in% c(0, 1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_prescatb1_combined$Age_Group <- ifelse(df_filtered_prescatb1_combined$AGE %in% c(1, 2), "18-34", "35+")
df_filtered_prescatb1_combined$No_Sometimes <- df_filtered_prescatb1_combined$PRESCATB1 %in% c(1, 3)
table_prescatb1_combined <- table(df_filtered_prescatb1_combined$No_Sometimes, df_filtered_prescatb1_combined$Age_Group)
# Adjust the table to have 'Yes' and 'No+Sometimes' as row names
rownames(table_prescatb1_combined) <- c("Yes", "No_Sometimes")
# Perform the Chi-Squared test
chi_result_prescatb1_combined <- chisq.test(table_prescatb1_combined)
# Calculate the odds ratio and confidence interval
odds_ratio_prescatb1_combined <- oddsratio(table_prescatb1_combined, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_prescatb1_combined, caption = "Contingency Table: Age vs. Following Prescription for Antibiotics (Yes vs. No+Sometimes)"))
# Print the results of the Chi-Squared test
print(chi_result_prescatb1_combined)
# Print the odds ratio and confidence interval
print(odds_ratio_prescatb1_combined)

---------------------------------------------------------------------------------------------------------------------
  
  ##ARRETATB Do you stop taking antibiotics when symptoms start to disappear?
  ##(Always=7.3%) (Sometimes=20.4%) (Always+Sometimes=27.7%)
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
df <- Database_simplified
############### 1st scenario= Always
df_filtered_arretatb <- df[df$ARRETATB %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_arretatb$Age_Group <- ifelse(df_filtered_arretatb$AGE %in% c(1, 2), "18-34", "35+")
table_arretatb <- table(df_filtered_arretatb$ARRETATB, df_filtered_arretatb$Age_Group)
# (Restante do script permanece o mesmo, substituindo 'GENRE' por 'Age_Group')
# Add descriptive labels to the rows and columns
rownames(table_arretatb) <- c("Always", "Never")
# Perform the Chi-Squared test
chi_result_arretatb <- chisq.test(table_arretatb)
# Calculate the odds ratio and confidence interval
odds_ratio_arretatb <- oddsratio(table_arretatb, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_arretatb, caption = "Contingency Table: Age vs. Stopping Antibiotics Always vs. Never"))
# Print the results of the Chi-Squared test
print(chi_result_arretatb)
# Print the odds ratio and confidence interval
print(odds_ratio_arretatb)

################# 2nd Cenario: Sometimes
df_filtered_arretatb_sometimes <- df[df$ARRETATB %in% c(1, 2) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_arretatb_sometimes$Age_Group <- ifelse(df_filtered_arretatb_sometimes$AGE %in% c(1, 2), "18-34", "35+")
table_arretatb_sometimes <- table(df_filtered_arretatb_sometimes$ARRETATB == 2, df_filtered_arretatb_sometimes$Age_Group)
# Add descriptive labels to the rows and columns
rownames(table_arretatb_sometimes) <- c("Never", "Sometimes")
# Perform the Chi-Squared test
chi_result_arretatb_sometimes <- chisq.test(table_arretatb_sometimes)
# Calculate the odds ratio and confidence interval
odds_ratio_arretatb_sometimes <- oddsratio(table_arretatb_sometimes, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_arretatb_sometimes, caption = "Contingency Table: Age vs. Stopping Antibiotics Sometimes vs. Never"))
# Print the results of the Chi-Squared test
print(chi_result_arretatb_sometimes)
# Print the odds ratio and confidence interval
print(odds_ratio_arretatb_sometimes)

############### #3rd scenario= Sometimes+Always
df_filtered_arretatb_combined <- df[df$ARRETATB %in% c(0, 1, 2) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_arretatb_combined$Age_Group <- ifelse(df_filtered_arretatb_combined$AGE %in% c(1, 2), "18-34", "35+")
df_filtered_arretatb_combined$Sometimes_Always <- df_filtered_arretatb_combined$ARRETATB %in% c(0, 2)
table_arretatb_combined <- table(df_filtered_arretatb_combined$Sometimes_Always, df_filtered_arretatb_combined$Age_Group)
# Add descriptive labels to the rows and columns
rownames(table_arretatb_combined) <- c("Never", "Sometimes_Always")
# Perform the Chi-Squared test
chi_result_arretatb_combined <- chisq.test(table_arretatb_combined)
# Calculate the odds ratio and confidence interval
odds_ratio_arretatb_combined <- oddsratio(table_arretatb_combined, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_arretatb_combined, caption = "Contingency Table: Age vs. Stopping Antibiotics (Sometimes+Always vs. Never)"))
# Print the results of the Chi-Squared test
print(chi_result_arretatb_combined)
# Print the odds ratio and confidence interval
print(odds_ratio_arretatb_combined)

---------------------------------------------------------------------------------------------------------------------
  
  ##ATBORAL1 Have you ever taken an oral antibiotic treatment (by mouth) without a medical prescription? (Yes=12.3%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified
df_filtered_atboral <- df[df$ATBORAL1 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atboral$Age_Group <- ifelse(df_filtered_atboral$AGE %in% c(1, 2), "18-34", "35+")
table_atboral <- table(df_filtered_atboral$ATBORAL1, df_filtered_atboral$Age_Group)
# Add descriptive labels to the rows and columns
rownames(table_atboral) <- c("Yes", "No")
# Perform the Chi-Squared test
chi_result_atboral <- chisq.test(table_atboral)
# Calculate the odds ratio and confidence interval
odds_ratio_atboral <- oddsratio(table_atboral, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atboral, caption = "Contingency Table: Age vs. Taking Oral Antibiotics Without Prescription (Yes vs. No)"))
# Print the results of the Chi-Squared test
print(chi_result_atboral)
# Print the odds ratio and confidence interval
print(odds_ratio_atboral)

--------------------------------------------------------------------------------------------------------
  
  ### ATBANI1 I can exchange resistant bacteria with my pet (False=23.2%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified  
df_filtered_atbani1 <- df[df$ATBANI1 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbani1$Age_Group <- ifelse(df_filtered_atbani1$AGE %in% c(1, 2), "18-34", "35+")
table_atbani1 <- table(df_filtered_atbani1$ATBANI1, df_filtered_atbani1$Age_Group)
rownames(table_atbani1) <- c("True", "False")
colnames(table_atbani1) <- c("18-34", "35+")
# Perform the Chi-Squared test
chi_result_atbani1 <- chisq.test(table_atbani1)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani1 <- oddsratio(table_atbani1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani1, caption = "Contingency Table: Age vs. Exchanging Resistant Bacteria with Pets (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani1)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani1)

---------------------------------------------------------------------------------------------------------------------
  
  ### ATBANI2=The use of antibiotics in livestock and crops can increase the 
  #presence of resistant bacteria in the environment (False=14.7%)
  
  df_filtered_atbani2 <- df[df$ATBANI2 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbani2$Age_Group <- ifelse(df_filtered_atbani2$AGE %in% c(1, 2), "18-34", "35+")
table_atbani2 <- table(df_filtered_atbani2$ATBANI2, df_filtered_atbani2$Age_Group)
rownames(table_atbani2) <- c("True", "False")
colnames(table_atbani2) <- c("18-34", "35+")
# Perform the Chi-Squared test
chi_result_atbani2 <- chisq.test(table_atbani2)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani2 <- oddsratio(table_atbani2, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani2, caption = "Contingency Table: Age vs. Antibiotics in Livestock and Crops Affecting Environment (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani2)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani2)


--------------------------------------------------------------------------------------------------------------------
  
  ##### ATBANI3	The use of antibiotics in livestock and crops can affect me directly
  ##(I can get resistant bacteria in my body) (False=26.3%)
  
  df_filtered_atbani3 <- df[df$ATBANI3 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbani3$Age_Group <- ifelse(df_filtered_atbani3$AGE %in% c(1, 2), "18-34", "35+")
table_atbani3 <- table(df_filtered_atbani3$ATBANI3, df_filtered_atbani3$Age_Group)
rownames(table_atbani3) <- c("True", "False")
colnames(table_atbani3) <- c("18-34", "35+")
# Perform the Chi-Squared test
chi_result_atbani3 <- chisq.test(table_atbani3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani3 <- oddsratio(table_atbani3, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani3, caption = "Contingency Table: Age vs. Antibiotics in Livestock and Crops Affecting Humans Directly (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani3)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani3)

-------------------------------------------------------------------------------------------------------------------
  ##### ATBANI4	Resistant bacteria are only found in hospitals (True=10.8%)
  
  df_filtered_atbani4 <- df[df$ATBANI4 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbani4$Age_Group <- ifelse(df_filtered_atbani4$AGE %in% c(1, 2), "18-34", "35+")
table_atbani4 <- table(df_filtered_atbani4$ATBANI4, df_filtered_atbani4$Age_Group)
rownames(table_atbani4) <- c("True", "False")
colnames(table_atbani4) <- c("18-34", "35+")
# Perform the Chi-Squared test
chi_result_atbani4 <- chisq.test(table_atbani4)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani4 <- oddsratio(table_atbani4, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani4, caption = "Contingency Table: Age vs. Resistant Bacteria Found Only in Hospitals (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani4)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani4)

----------------------------------------------------------------------------------------------------------------------
  
  #####RESATB1	Antibiotic resistance occurs when your body becomes resistant to antibiotics and they
  ##no longer work as well (True=58.3%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified
df_filtered_resatb1 <- df[df$RESATB1 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb1$Age_Group <- ifelse(df_filtered_resatb1$AGE %in% c(1, 2), "18-34", "35+")
table_resatb1 <- table(df_filtered_resatb1$RESATB1, df_filtered_resatb1$Age_Group)
rownames(table_resatb1) <- c("True", "False")
colnames(table_resatb1) <- c("18-34", "35+")
# Perform the Chi-Squared test
chi_result_resatb1 <- chisq.test(table_resatb1)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb1 <- oddsratio(table_resatb1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb1, caption = "Contingency Table: Age vs. Understanding of Antibiotic Resistance (RESATB1: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb1)
print(odds_ratio_resatb1)

-------------------------------------------------------------------------------------------------------------------
  
  #####RESATB2	Many infections are becoming increasingly resistant to antibiotic treatment  (False=12.5%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb2 <- df[df$RESATB2 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb2$Age_Group <- ifelse(df_filtered_resatb2$AGE %in% c(1, 2), "18-34", "35+")
table_resatb2 <- table(df_filtered_resatb2$RESATB2, df_filtered_resatb2$Age_Group)
rownames(table_resatb2) <- c("True", "False")
colnames(table_resatb2) <- c("18-34", "35+")
# Perform the Chi-Squared test
chi_result_resatb2 <- chisq.test(table_resatb2)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb2 <- oddsratio(table_resatb2, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb2, caption = "Contingency Table: Age vs. Perception of Increasing Infection Resistance (RESATB2: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb2)
print(odds_ratio_resatb2)

---------------------------------------------------------------------------------------------------------------------
  #####RESATB3	If bacteria are resistant to antibiotics, it can be very difficult or impossible to treat the infections they cause (False=16.7%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb3 <- df[df$RESATB3 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb3$Age_Group <- ifelse(df_filtered_resatb3$AGE %in% c(1, 2), "18-34", "35+")
table_resatb3 <- table(df_filtered_resatb3$RESATB3, df_filtered_resatb3$Age_Group)
rownames(table_resatb3) <- c("True", "False")
colnames(table_resatb3) <- c("18-34", "35+")
# Perform the Chi-Squared test
chi_result_resatb3 <- chisq.test(table_resatb3)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb3 <- oddsratio(table_resatb3, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb3, caption = "Contingency Table: Age vs. Perception of Difficulty Treating Infections (RESATB3: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb3)
print(odds_ratio_resatb3)
----------------------------------------------------------------------------------------------------------------------
  #####RESATB4	Antibiotic resistance is an issue that could affect me or my family (False=11.8%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb4 <- df[df$RESATB4 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb4$Age_Group <- ifelse(df_filtered_resatb4$AGE %in% c(1, 2), "18-34", "35+")
table_resatb4 <- table(df_filtered_resatb4$RESATB4, df_filtered_resatb4$Age_Group)
rownames(table_resatb4) <- c("True", "False")
colnames(table_resatb4) <- c("18-34", "35+")
# Perform the Chi-Squared test
chi_result_resatb4 <- chisq.test(table_resatb4)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb4 <- oddsratio(table_resatb4, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb4, caption = "Contingency Table: Age vs. Perception of Antibiotic Resistance Affecting One's Family (RESATB4: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb4)
print(odds_ratio_resatb4)

---------------------------------------------------------------------------------------------------------------------
  #####RESATB5	Antibiotic resistance is an issue in other countries but not here (True=9.9%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb5 <- df[df$RESATB5 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb5$Age_Group <- ifelse(df_filtered_resatb5$AGE %in% c(1, 2), "18-34", "35+")
table_resatb5 <- table(df_filtered_resatb5$RESATB5, df_filtered_resatb5$Age_Group)
rownames(table_resatb5) <- c("True", "False")
colnames(table_resatb5) <- c("18-34", "35+")
# Perform the Chi-Squared test
chi_result_resatb5 <- chisq.test(table_resatb5)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb5 <- oddsratio(table_resatb5, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb5, caption = "Contingency Table: Age vs. Perception of Antibiotic Resistance as an Issue Only in Other Countries (RESATB5: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb5)
print(odds_ratio_resatb5)
---------------------------------------------------------------------------------------------------------------------  
  
  #####RESATB6	Antibiotic resistance is only a problem for people who take antibiotics regularly (True=17.5%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb6 <- df[df$RESATB6 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb6$Age_Group <- ifelse(df_filtered_resatb6$AGE %in% c(1, 2), "18-34", "35+")
table_resatb6 <- table(df_filtered_resatb6$RESATB6, df_filtered_resatb6$Age_Group)
rownames(table_resatb6) <- c("True", "False")
colnames(table_resatb6) <- c("18-34", "35+")
# Perform the Chi-Squared test
chi_result_resatb6 <- chisq.test(table_resatb6)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb6 <- oddsratio(table_resatb6, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb6, caption = "Contingency Table: Age vs. Perception of Antibiotic Resistance as a Problem Only for Regular Antibiotic Users (RESATB6: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb6)
print(odds_ratio_resatb6)

--------------------------------------------------------------------------------------------------------------------- 
  #####RESATB7	Bacteria that are resistant to antibiotics can be spread from person to person (False=20.2%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb7 <- df[df$RESATB7 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb7$Age_Group <- ifelse(df_filtered_resatb7$AGE %in% c(1, 2), "18-34", "35+")
table_resatb7 <- table(df_filtered_resatb7$RESATB7, df_filtered_resatb7$Age_Group)
rownames(table_resatb7) <- c("True", "False")
colnames(table_resatb7) <- c("18-34", "35+")
# Perform the Chi-Squared test
chi_result_resatb7 <- chisq.test(table_resatb7)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb7 <- oddsratio(table_resatb7, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb7, caption = "Contingency Table: Age vs. Perception of Bacteria Transmission Person to Person (RESATB7: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb7)
print(odds_ratio_resatb7)

--------------------------------------------------------------------------------------------------------------------
  #####RESATB8	Antibiotic-resistant infections could make medical procedures like surgery, organ transplants,
  ##and cancer treatment much more dangerous (False=12.0%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb8 <- df[df$RESATB8 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb8$Age_Group <- ifelse(df_filtered_resatb8$AGE %in% c(1, 2), "18-34", "35+")
table_resatb8 <- table(df_filtered_resatb8$RESATB8, df_filtered_resatb8$Age_Group)
rownames(table_resatb8) <- c("True", "False")
colnames(table_resatb8) <- c("18-34", "35+")
# Perform the Chi-Squared test
chi_result_resatb8 <- chisq.test(table_resatb8)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb8 <- oddsratio(table_resatb8, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb8, caption = "Contingency Table: Age vs. Perception of Antibiotic-Resistant Infections and Medical Procedures (RESATB8: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb8)
print(odds_ratio_resatb8)

--------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL1	Farmers should give fewer antibiotics to food-producing animals 
  
  ##################### 1st scenario (Strongly desagree=8.68%) vs. Strongly Agree
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl1_scenario1 <- df[df$ATBRGL1 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl1_scenario1$Age_Group <- ifelse(df_filtered_atbrgl1_scenario1$AGE %in% c(1, 2), "18-34", "35+")
table_atbrgl1_scenario1 <- table(df_filtered_atbrgl1_scenario1$ATBRGL1, df_filtered_atbrgl1_scenario1$Age_Group)
rownames(table_atbrgl1_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl1_scenario1) <- c("18-34", "35+")
# Perform the Chi-Squared test
chi_result_atbrgl1_scenario1 <- chisq.test(table_atbrgl1_scenario1)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl1_scenario1 <- oddsratio(table_atbrgl1_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl1_scenario1, caption = "Contingency Table: Age vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_atbrgl1_scenario1)
print(odds_ratio_atbrgl1_scenario1)

############################# 2nd scenario Farmers should give fewer antibiotics to
##food-producing animals (Neither agree nor desagree=22.6%) vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl1_scenario2 <- df[df$ATBRGL1 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl1_scenario2$Age_Group <- ifelse(df_filtered_atbrgl1_scenario2$AGE %in% c(1, 2), "18-34", "35+")
table_atbrgl1_scenario2 <- table(df_filtered_atbrgl1_scenario2$ATBRGL1, df_filtered_atbrgl1_scenario2$Age_Group)
rownames(table_atbrgl1_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl1_scenario2) <- c("18-34", "35+")
# Perform the Chi-Squared test
chi_result_atbrgl1_scenario2 <- chisq.test(table_atbrgl1_scenario2)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl1_scenario2 <- oddsratio(table_atbrgl1_scenario2, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl1_scenario2, caption = "Contingency Table: Age vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Neither Agree Nor Disagree)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_atbrgl1_scenario2)
print(odds_ratio_atbrgl1_scenario2)

############################# 3rd scenario (Strongly desagree + Neither agree nor desagree=31.28%) vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl1_scenario3 <- df[df$ATBRGL1 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl1_scenario3$Age_Group <- ifelse(df_filtered_atbrgl1_scenario3$AGE %in% c(1, 2), "18-34", "35+")
df_filtered_atbrgl1_scenario3$Disagree_Neither <- df_filtered_atbrgl1_scenario3$ATBRGL1 %in% c(1, 2)
table_atbrgl1_scenario3 <- table(df_filtered_atbrgl1_scenario3$Disagree_Neither, df_filtered_atbrgl1_scenario3$Age_Group)
rownames(table_atbrgl1_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl1_scenario3) <- c("18-34", "35+")
# Perform the Chi-Squared test
chi_result_atbrgl1_scenario3 <- chisq.test(table_atbrgl1_scenario3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl1_scenario3 <- oddsratio(table_atbrgl1_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl1_scenario3, caption = "Contingency Table: Age vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree + Neither)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_atbrgl1_scenario3)
print(odds_ratio_atbrgl1_scenario3)

--------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL2	People should not keep antibiotics and use them later for other illnesses  
  
  ############################# 1st scenario Strongly desagree vs. Strongly Agree
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the database
df <- Database_simplified
## Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_atbrgl2_scenario1 <- df[df$ATBRGL2 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl2_scenario1$Age_Group <- ifelse(df_filtered_atbrgl2_scenario1$AGE %in% c(1, 2), "18-34", "35+")
table_atbrgl2_scenario1 <- table(df_filtered_atbrgl2_scenario1$ATBRGL2, df_filtered_atbrgl2_scenario1$Age_Group)
rownames(table_atbrgl2_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl2_scenario1) <- c("18-34", "35+")
# Perform Chi-Squared test
chi_result_atbrgl2_scenario1 <- chisq.test(table_atbrgl2_scenario1)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl2_scenario1 <- oddsratio(table_atbrgl2_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl2_scenario1, caption = "Contingency Table: Age vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl2_scenario1)
print(odds_ratio_atbrgl2_scenario1)

############################# 2nd scenario Neither agree nor desagree vs. Strongly Agree
# Filter for 'Strongly Agree' (3) and 'Neither Agree Nor Disagree' (2) responses for ATBRGL2
df_filtered_atbrgl2_scenario2 <- df[df$ATBRGL2 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl2_scenario2$Age_Group <- ifelse(df_filtered_atbrgl2_scenario2$AGE %in% c(1, 2), "18-34", "35+")
table_atbrgl2_scenario2 <- table(df_filtered_atbrgl2_scenario2$ATBRGL2, df_filtered_atbrgl2_scenario2$Age_Group)
rownames(table_atbrgl2_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl2_scenario2) <- c("18-34", "35+")
# Perform Chi-Squared test
chi_result_atbrgl2_scenario2 <- chisq.test(table_atbrgl2_scenario2)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl2_scenario2 <- oddsratio(table_atbrgl2_scenario2, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl2_scenario2, caption = "Contingency Table: Age vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl2_scenario2)
print(odds_ratio_atbrgl2_scenario2)


############################# 3rd scenario Neither agree nor desagree + Stringly Disagree vs. Strongly Agree
df_filtered_atbrgl2_scenario3 <- df[df$ATBRGL2 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl2_scenario3$Age_Group <- ifelse(df_filtered_atbrgl2_scenario3$AGE %in% c(1, 2), "18-34", "35+")
df_filtered_atbrgl2_scenario3$Disagree_Neither <- df_filtered_atbrgl2_scenario3$ATBRGL2 %in% c(1, 2)
table_atbrgl2_scenario3 <- table(df_filtered_atbrgl2_scenario3$Disagree_Neither, df_filtered_atbrgl2_scenario3$Age_Group)
rownames(table_atbrgl2_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl2_scenario3) <- c("18-34", "35+")
# Perform the Chi-Squared test
chi_result_atbrgl2_scenario3 <- chisq.test(table_atbrgl2_scenario3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl2_scenario3 <- oddsratio(table_atbrgl2_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl2_scenario3, caption = "Contingency Table: Age vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl2_scenario3)
print(odds_ratio_atbrgl2_scenario3)

--------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL3 Parents should make sure all of their children’s vaccinations are up-to-date 
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)

####1st scenario
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl3_scenario1 <- df[df$ATBRGL3 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl3_scenario1$Age_Group <- ifelse(df_filtered_atbrgl3_scenario1$AGE %in% c(1, 2), "18-34", "35+")
table_atbrgl3_scenario1 <- table(df_filtered_atbrgl3_scenario1$ATBRGL3, df_filtered_atbrgl3_scenario1$Age_Group)
rownames(table_atbrgl3_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl3_scenario1) <- c("18-34", "35+")
# Perform Chi-Squared test
chi_result_atbrgl3_scenario1 <- chisq.test(table_atbrgl3_scenario1)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl3_scenario1 <- oddsratio(table_atbrgl3_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl3_scenario1, caption = "Contingency Table: Age vs. Opinion on Children's Vaccinations (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl3_scenario1)
print(odds_ratio_atbrgl3_scenario1)

### 2nd Scenario
df_filtered_atbrgl3_scenario2 <- df[df$ATBRGL3 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl3_scenario2$Age_Group <- ifelse(df_filtered_atbrgl3_scenario2$AGE %in% c(1, 2), "18-34", "35+")
table_atbrgl3_scenario2 <- table(df_filtered_atbrgl3_scenario2$ATBRGL3, df_filtered_atbrgl3_scenario2$Age_Group)
rownames(table_atbrgl3_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl3_scenario2) <- c("18-34", "35+")
# Perform Chi-Squared test
chi_result_atbrgl3_scenario2 <- chisq.test(table_atbrgl3_scenario2)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl3_scenario2 <- oddsratio(table_atbrgl3_scenario2, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl3_scenario2, caption = "Contingency Table: Age vs. Opinion on Children's Vaccinations (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl3_scenario2)
print(odds_ratio_atbrgl3_scenario2)

## 3rd scenario
df_filtered_atbrgl3_scenario3 <- df[df$ATBRGL3 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl3_scenario3$Age_Group <- ifelse(df_filtered_atbrgl3_scenario3$AGE %in% c(1, 2), "18-34", "35+")
df_filtered_atbrgl3_scenario3$Disagree_Neither <- df_filtered_atbrgl3_scenario3$ATBRGL3 %in% c(1, 2)
table_atbrgl3_scenario3 <- table(df_filtered_atbrgl3_scenario3$Disagree_Neither, df_filtered_atbrgl3_scenario3$Age_Group)
rownames(table_atbrgl3_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl3_scenario3) <- c("18-34", "35+")
# Perform the Chi-Squared test
chi_result_atbrgl3_scenario3 <- chisq.test(table_atbrgl3_scenario3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl3_scenario3 <- oddsratio(table_atbrgl3_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl3_scenario3, caption = "Contingency Table: Age vs. Opinion on Children's Vaccinations (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl3_scenario3)
print(odds_ratio_atbrgl3_scenario3)

---------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL4 People should wash their hands regularly
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

## Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_atbrgl4_scenario1 <- df[df$ATBRGL4 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl4_scenario1$Age_Group <- ifelse(df_filtered_atbrgl4_scenario1$AGE %in% c(1, 2), "18-34", "35+")
table_atbrgl4_scenario1 <- table(df_filtered_atbrgl4_scenario1$ATBRGL4, df_filtered_atbrgl4_scenario1$Age_Group)
rownames(table_atbrgl4_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl4_scenario1) <- c("18-34", "35+")
chi_result_atbrgl4_scenario1 <- chisq.test(table_atbrgl4_scenario1)
odds_ratio_atbrgl4_scenario1 <- oddsratio(table_atbrgl4_scenario1, conf.level = 0.95)$measure
print(kable(table_atbrgl4_scenario1, caption = "Contingency Table: Age vs. Hand Washing Importance (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl4_scenario1)
print(odds_ratio_atbrgl4_scenario1)

## Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl4_scenario2 <- df[df$ATBRGL4 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl4_scenario2$Age_Group <- ifelse(df_filtered_atbrgl4_scenario2$AGE %in% c(1, 2), "18-34", "35+")
table_atbrgl4_scenario2 <- table(df_filtered_atbrgl4_scenario2$ATBRGL4, df_filtered_atbrgl4_scenario2$Age_Group)
rownames(table_atbrgl4_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl4_scenario2) <- c("18-34", "35+")
chi_result_atbrgl4_scenario2 <- chisq.test(table_atbrgl4_scenario2)
odds_ratio_atbrgl4_scenario2 <- oddsratio(table_atbrgl4_scenario2, conf.level = 0.95)$measure
print(kable(table_atbrgl4_scenario2, caption = "Contingency Table: Age vs. Hand Washing Importance (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl4_scenario2)
print(odds_ratio_atbrgl4_scenario2)

## Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl4_scenario3 <- df[df$ATBRGL4 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl4_scenario3$Age_Group <- ifelse(df_filtered_atbrgl4_scenario3$AGE %in% c(1, 2), "18-34", "35+")
df_filtered_atbrgl4_scenario3$Disagree_Neither <- df_filtered_atbrgl4_scenario3$ATBRGL4 %in% c(1, 2)
table_atbrgl4_scenario3 <- table(df_filtered_atbrgl4_scenario3$Disagree_Neither, df_filtered_atbrgl4_scenario3$Age_Group)
rownames(table_atbrgl4_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl4_scenario3) <- c("18-34", "35+")
chi_result_atbrgl4_scenario3 <- chisq.test(table_atbrgl4_scenario3)
odds_ratio_atbrgl4_scenario3 <- oddsratio(table_atbrgl4_scenario3, conf.level = 0.95)$measure
print(kable(table_atbrgl4_scenario3, caption = "Contingency Table: Age vs. Hand Washing Importance (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl4_scenario3)
print(odds_ratio_atbrgl4_scenario3)

---------------------------------------------------------------------------------------------------------------------
  
  #ATBRGL5 Doctors should only prescribe antibiotics when they are needed 
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)

# Load the Database_simplified dataframe
df <- Database_simplified

## Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_atbrgl5_scenario1 <- df[df$ATBRGL5 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl5_scenario1$Age_Group <- ifelse(df_filtered_atbrgl5_scenario1$AGE %in% c(1, 2), "18-34", "35+")
table_atbrgl5_scenario1 <- table(df_filtered_atbrgl5_scenario1$ATBRGL5, df_filtered_atbrgl5_scenario1$Age_Group)
rownames(table_atbrgl5_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl5_scenario1) <- c("18-34", "35+")
chi_result_atbrgl5_scenario1 <- chisq.test(table_atbrgl5_scenario1)
odds_ratio_atbrgl5_scenario1 <- oddsratio(table_atbrgl5_scenario1, conf.level = 0.95)$measure
print(kable(table_atbrgl5_scenario1, caption = "Contingency Table: Age vs. Antibiotic Prescription Necessity (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl5_scenario1)
print(odds_ratio_atbrgl5_scenario1)

## Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl5_scenario2 <- df[df$ATBRGL5 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl5_scenario2$Age_Group <- ifelse(df_filtered_atbrgl5_scenario2$AGE %in% c(1, 2), "18-34", "35+")
table_atbrgl5_scenario2 <- table(df_filtered_atbrgl5_scenario2$ATBRGL5, df_filtered_atbrgl5_scenario2$Age_Group)
rownames(table_atbrgl5_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl5_scenario2) <- c("18-34", "35+")
chi_result_atbrgl5_scenario2 <- chisq.test(table_atbrgl5_scenario2)
odds_ratio_atbrgl5_scenario2 <- oddsratio(table_atbrgl5_scenario2, conf.level = 0.95)$measure
print(kable(table_atbrgl5_scenario2, caption = "Contingency Table: Age vs. Antibiotic Prescription Necessity (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl5_scenario2)
print(odds_ratio_atbrgl5_scenario2)

## Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl5_scenario3 <- df[df$ATBRGL5 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl5_scenario3$Age_Group <- ifelse(df_filtered_atbrgl5_scenario3$AGE %in% c(1, 2), "18-34", "35+")
df_filtered_atbrgl5_scenario3$Disagree_Neither <- df_filtered_atbrgl5_scenario3$ATBRGL5 %in% c(1, 2)
table_atbrgl5_scenario3 <- table(df_filtered_atbrgl5_scenario3$Disagree_Neither, df_filtered_atbrgl5_scenario3$Age_Group)
rownames(table_atbrgl5_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl5_scenario3) <- c("18-34", "35+")
chi_result_atbrgl5_scenario3 <- chisq.test(table_atbrgl5_scenario3)
odds_ratio_atbrgl5_scenario3 <- oddsratio(table_atbrgl5_scenario3, conf.level = 0.95)$measure
print(kable(table_atbrgl5_scenario3, caption = "Contingency Table: Age vs. Antibiotic Prescription Necessity (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl5_scenario3)
print(odds_ratio_atbrgl5_scenario3)

----------------------------------------------------------------------------------------------------------------------
  
  ##ATBRGL6= People should only use antibiotics when prescribed by a doctor or nurse
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

## Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_atbrgl6_scenario1 <- df[df$ATBRGL6 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl6_scenario1$Age_Group <- ifelse(df_filtered_atbrgl6_scenario1$AGE %in% c(1, 2), "18-34", "35+")
table_atbrgl6_scenario1 <- table(df_filtered_atbrgl6_scenario1$ATBRGL6, df_filtered_atbrgl6_scenario1$Age_Group)
rownames(table_atbrgl6_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl6_scenario1) <- c("18-34", "35+")
chi_result_atbrgl6_scenario1 <- chisq.test(table_atbrgl6_scenario1)
odds_ratio_atbrgl6_scenario1 <- oddsratio(table_atbrgl6_scenario1, conf.level = 0.95)$measure
print(kable(table_atbrgl6_scenario1, caption = "Contingency Table: Age vs. Antibiotic only when prescribed (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl6_scenario1)
print(odds_ratio_atbrgl6_scenario1)

## Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl6_scenario2 <- df[df$ATBRGL6 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl6_scenario2$Age_Group <- ifelse(df_filtered_atbrgl6_scenario2$AGE %in% c(1, 2), "18-34", "35+")
table_atbrgl6_scenario2 <- table(df_filtered_atbrgl6_scenario2$ATBRGL6, df_filtered_atbrgl6_scenario2$Age_Group)
rownames(table_atbrgl6_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl6_scenario2) <- c("18-34", "35+")
chi_result_atbrgl6_scenario2 <- chisq.test(table_atbrgl6_scenario2)
odds_ratio_atbrgl6_scenario2 <- oddsratio(table_atbrgl6_scenario2, conf.level = 0.95)$measure
print(kable(table_atbrgl6_scenario2, caption = "Contingency Table: Age vs. Antibiotic only when prescribed (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl6_scenario2)
print(odds_ratio_atbrgl6_scenario2)

## Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl6_scenario3 <- df[df$ATBRGL6 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl6_scenario3$Age_Group <- ifelse(df_filtered_atbrgl6_scenario3$AGE %in% c(1, 2), "18-34", "35+")
df_filtered_atbrgl6_scenario3$Disagree_Neither <- df_filtered_atbrgl6_scenario3$ATBRGL6 %in% c(1, 2)
table_atbrgl6_scenario3 <- table(df_filtered_atbrgl6_scenario3$Disagree_Neither, df_filtered_atbrgl6_scenario3$Age_Group)
rownames(table_atbrgl6_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl6_scenario3) <- c("18-34", "35+")
chi_result_atbrgl6_scenario3 <- chisq.test(table_atbrgl6_scenario3)
odds_ratio_atbrgl6_scenario3 <- oddsratio(table_atbrgl6_scenario3, conf.level = 0.95)$measure
print(kable(table_atbrgl6_scenario3, caption = "Contingency Table: Age vs. Antibiotic only when prescribed (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl6_scenario3)
print(odds_ratio_atbrgl6_scenario3)

----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM1= Antibiotic resistance is one of the biggest problems the world faces
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_resdim1_scenario1 <- df[df$RESDIM1 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim1_scenario1$Age_Group <- ifelse(df_filtered_resdim1_scenario1$AGE %in% c(1, 2), "18-34", "35+")
table_resdim1_scenario1 <- table(df_filtered_resdim1_scenario1$RESDIM1, df_filtered_resdim1_scenario1$Age_Group)
rownames(table_resdim1_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim1_scenario1) <- c("18-34", "35+")
chi_result_resdim1_scenario1 <- chisq.test(table_resdim1_scenario1)
odds_ratio_resdim1_scenario1 <- oddsratio(table_resdim1_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim1_scenario1, caption = "Contingency Table: Age vs. Perception of Antibiotic Resistance as a Global Problem (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_resdim1_scenario1)
print(odds_ratio_resdim1_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim1_scenario2 <- df[df$RESDIM1 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim1_scenario2$Age_Group <- ifelse(df_filtered_resdim1_scenario2$AGE %in% c(1, 2), "18-34", "35+")
table_resdim1_scenario2 <- table(df_filtered_resdim1_scenario2$RESDIM1, df_filtered_resdim1_scenario2$Age_Group)
rownames(table_resdim1_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_resdim1_scenario2) <- c("18-34", "35+")
chi_result_resdim1_scenario2 <- chisq.test(table_resdim1_scenario2)
odds_ratio_resdim1_scenario2 <- oddsratio(table_resdim1_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim1_scenario2, caption = "Contingency Table: Age vs. Perception of Antibiotic Resistance as a Global Problem (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim1_scenario2)
print(odds_ratio_resdim1_scenario2)

# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim1_scenario3 <- df[df$RESDIM1 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim1_scenario3$Age_Group <- ifelse(df_filtered_resdim1_scenario3$AGE %in% c(1, 2), "18-34", "35+")
df_filtered_resdim1_scenario3$Disagree_Neither <- df_filtered_resdim1_scenario3$RESDIM1 %in% c(1, 2)
table_resdim1_scenario3 <- table(df_filtered_resdim1_scenario3$Disagree_Neither, df_filtered_resdim1_scenario3$Age_Group)
rownames(table_resdim1_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_resdim1_scenario3) <- c("18-34", "35+")
chi_result_resdim1_scenario3 <- chisq.test(table_resdim1_scenario3)
odds_ratio_resdim1_scenario3 <- oddsratio(table_resdim1_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim1_scenario3, caption = "Contingency Table: Age vs. Perception of Antibiotic Resistance as a Global Problem (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_resdim1_scenario3)
print(odds_ratio_resdim1_scenario3)

----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM2= Medical experts will solve the problem of antibiotic resistance before it becomes too serious 
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Load the Database_simplified dataframe
df <- read_excel("C:/Database_simplified.xlsx")

# Scenario 1: Strongly Agree vs. Strongly Disagree
df_filtered_resdim2_scenario1 <- df[df$RESDIM2 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim2_scenario1$Age_Group <- ifelse(df_filtered_resdim2_scenario1$AGE %in% c(1, 2), "18-34", "35+")
table_resdim2_scenario1 <- table(df_filtered_resdim2_scenario1$RESDIM2, df_filtered_resdim2_scenario1$Age_Group)
rownames(table_resdim2_scenario1) <- c("Strongly Agree", "Strongly Disagree")
colnames(table_resdim2_scenario1) <- c("18-34", "35+")
chi_result_resdim2_scenario1 <- chisq.test(table_resdim2_scenario1)
odds_ratio_resdim2_scenario1 <- oddsratio(table_resdim2_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim2_scenario1, caption = "Contingency Table: Age vs. Belief in Solving Antibiotic Resistance (Strongly Disagree vs. Strongly Agree)"))
print(chi_result_resdim2_scenario1)
print(odds_ratio_resdim2_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim2_scenario2 <- df[df$RESDIM2 %in% c(1, 2) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim2_scenario2$Age_Group <- ifelse(df_filtered_resdim2_scenario2$AGE %in% c(1, 2), "18-34", "35+")
table_resdim2_scenario2 <- table(df_filtered_resdim2_scenario2$RESDIM2, df_filtered_resdim2_scenario2$Age_Group)
rownames(table_resdim2_scenario2) <- c("Strongly Disagree", "Neither Agree Nor Disagree")
colnames(table_resdim2_scenario2) <- c("18-34", "35+")
chi_result_resdim2_scenario2 <- chisq.test(table_resdim2_scenario2)
odds_ratio_resdim2_scenario2 <- oddsratio(table_resdim2_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim2_scenario2, caption = "Contingency Table: Age vs. Belief in Solving Antibiotic Resistance (Strongly Disagree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim2_scenario2)
print(odds_ratio_resdim2_scenario2)

# Scenario 3: Strongly Agree + Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim2_scenario3 <- df[df$RESDIM2 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim2_scenario3$Age_Group <- ifelse(df_filtered_resdim2_scenario3$AGE %in% c(1, 2), "18-34", "35+")
df_filtered_resdim2_scenario3$Agree_Neither <- df_filtered_resdim2_scenario3$RESDIM2 %in% c(2, 3)
table_resdim2_scenario3 <- table(df_filtered_resdim2_scenario3$Agree_Neither, df_filtered_resdim2_scenario3$Age_Group)
rownames(table_resdim2_scenario3) <- c("Strongly Disagree", "Strongly Agree + Neither")
colnames(table_resdim2_scenario3) <- c("18-34", "35+")
chi_result_resdim2_scenario3 <- chisq.test(table_resdim2_scenario3)
odds_ratio_resdim2_scenario3 <- oddsratio(table_resdim2_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim2_scenario3, caption = "Contingency Table: Age vs. Belief in Solving Antibiotic Resistance (Strongly Disagree vs. Strongly Agree + Neither Agree Nor Disagree)"))
print(chi_result_resdim2_scenario3)
print(odds_ratio_resdim2_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM3= Everyone needs to use antibiotics responsibly
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_resdim3_scenario1 <- df[df$RESDIM3 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim3_scenario1$Age_Group <- ifelse(df_filtered_resdim3_scenario1$AGE %in% c(1, 2), "18-34", "35+")
table_resdim3_scenario1 <- table(df_filtered_resdim3_scenario1$RESDIM3, df_filtered_resdim3_scenario1$Age_Group)
rownames(table_resdim3_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim3_scenario1) <- c("18-34", "35+")
chi_result_resdim3_scenario1 <- chisq.test(table_resdim3_scenario1)
odds_ratio_resdim3_scenario1 <- oddsratio(table_resdim3_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim3_scenario1, caption = "Contingency Table: Age vs. Everyone needs to use antibiotics responsibly (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_resdim3_scenario1)
print(odds_ratio_resdim3_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim3_scenario2 <- df[df$RESDIM3 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim3_scenario2$Age_Group <- ifelse(df_filtered_resdim3_scenario2$AGE %in% c(1, 2), "18-34", "35+")
table_resdim3_scenario2 <- table(df_filtered_resdim3_scenario2$RESDIM3, df_filtered_resdim3_scenario2$Age_Group)
rownames(table_resdim3_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_resdim3_scenario2) <- c("18-34", "35+")
chi_result_resdim3_scenario2 <- chisq.test(table_resdim3_scenario2)
odds_ratio_resdim3_scenario2 <- oddsratio(table_resdim3_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim3_scenario2, caption = "Contingency Table: Age vs. Everyone needs to use antibiotics responsibly (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim3_scenario2)
print(odds_ratio_resdim3_scenario2)

# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim3_scenario3 <- df[df$RESDIM3 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim3_scenario3$Age_Group <- ifelse(df_filtered_resdim3_scenario3$AGE %in% c(1, 2), "18-34", "35+")
df_filtered_resdim3_scenario3$Disagree_Neither <- df_filtered_resdim3_scenario3$RESDIM3 %in% c(1, 2)
table_resdim3_scenario3 <- table(df_filtered_resdim3_scenario3$Disagree_Neither, df_filtered_resdim3_scenario3$Age_Group)
rownames(table_resdim3_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_resdim3_scenario3) <- c("18-34", "35+")
chi_result_resdim3_scenario3 <- chisq.test(table_resdim3_scenario3)
odds_ratio_resdim3_scenario3 <- oddsratio(table_resdim3_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim3_scenario3, caption = "Contingency Table: Age vs. Everyone needs to use antibiotics responsibly (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_resdim3_scenario3)
print(odds_ratio_resdim3_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM4= People like me can't do much to stop antibiotic resistance
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Agree vs. Strongly Disagree
df_filtered_resdim4_scenario1 <- df[df$RESDIM4 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim4_scenario1$Age_Group <- ifelse(df_filtered_resdim4_scenario1$AGE %in% c(1, 2), "18-34", "35+")
table_resdim4_scenario1 <- table(df_filtered_resdim4_scenario1$RESDIM4, df_filtered_resdim4_scenario1$Age_Group)
rownames(table_resdim4_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim4_scenario1) <- c("18-34", "35+")
chi_result_resdim4_scenario1 <- chisq.test(table_resdim4_scenario1)
odds_ratio_resdim4_scenario1 <- oddsratio(table_resdim4_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim4_scenario1, caption = "Contingency Table: Age vs. Belief in Individual Impact on Antibiotic Resistance (Strongly Disagree vs. Strongly Agree)"))
print(chi_result_resdim4_scenario1)
print(odds_ratio_resdim4_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim4_scenario2 <- df[df$RESDIM4 %in% c(1, 2) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim4_scenario2$Age_Group <- ifelse(df_filtered_resdim4_scenario2$AGE %in% c(1, 2), "18-34", "35+")
table_resdim4_scenario2 <- table(df_filtered_resdim4_scenario2$RESDIM4, df_filtered_resdim4_scenario2$Age_Group)
rownames(table_resdim4_scenario2) <- c("Strongly Disagree", "Neither Agree Nor Disagree")
colnames(table_resdim4_scenario2) <- c("18-34", "35+")
chi_result_resdim4_scenario2 <- chisq.test(table_resdim4_scenario2)
odds_ratio_resdim4_scenario2 <- oddsratio(table_resdim4_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim4_scenario2, caption = "Contingency Table: Age vs. Belief in Individual Impact on Antibiotic Resistance (Strongly Disagree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim4_scenario2)
print(odds_ratio_resdim4_scenario2)

# Scenario 3: Strongly Agree + Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim4_scenario3 <- df[df$RESDIM4 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim4_scenario3$Age_Group <- ifelse(df_filtered_resdim4_scenario3$AGE %in% c(1, 2), "18-34", "35+")
df_filtered_resdim4_scenario3$Agree_Neither <- df_filtered_resdim4_scenario3$RESDIM4 %in% c(2, 3)
table_resdim4_scenario3 <- table(df_filtered_resdim4_scenario3$Agree_Neither, df_filtered_resdim4_scenario3$Age_Group)
rownames(table_resdim4_scenario3) <- c("Strongly Disagree", "Strongly Agree + Neither")
colnames(table_resdim4_scenario3) <- c("18-34", "35+")
chi_result_resdim4_scenario3 <- chisq.test(table_resdim4_scenario3)
odds_ratio_resdim4_scenario3 <- oddsratio(table_resdim4_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim4_scenario3, caption = "Contingency Table: Age vs. Belief in Individual Impact on Antibiotic Resistance (Strongly Disagree vs. Strongly Agree + Neither Agree Nor Disagree)"))
print(chi_result_resdim4_scenario3)
print(odds_ratio_resdim4_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM5= I am worried about the impact that antibiotic resistance will have on my health and that of my family
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_resdim5_scenario1 <- df[df$RESDIM5 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim5_scenario1$Age_Group <- ifelse(df_filtered_resdim5_scenario1$AGE %in% c(1, 2), "18-34", "35+")
table_resdim5_scenario1 <- table(df_filtered_resdim5_scenario1$RESDIM5, df_filtered_resdim5_scenario1$Age_Group)
rownames(table_resdim5_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim5_scenario1) <- c("18-34", "35+")
chi_result_resdim5_scenario1 <- chisq.test(table_resdim5_scenario1)
odds_ratio_resdim5_scenario1 <- oddsratio(table_resdim5_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim5_scenario1, caption = "Contingency Table: Age vs. Impact of AMR on personal health and that of their family (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_resdim5_scenario1)
print(odds_ratio_resdim5_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim5_scenario2 <- df[df$RESDIM5 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim5_scenario2$Age_Group <- ifelse(df_filtered_resdim5_scenario2$AGE %in% c(1, 2), "18-34", "35+")
table_resdim5_scenario2 <- table(df_filtered_resdim5_scenario2$RESDIM5, df_filtered_resdim5_scenario2$Age_Group)
rownames(table_resdim5_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_resdim5_scenario2) <- c("18-34", "35+")
chi_result_resdim5_scenario2 <- chisq.test(table_resdim5_scenario2)
odds_ratio_resdim5_scenario2 <- oddsratio(table_resdim5_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim5_scenario2, caption = "Contingency Table: Age vs. Impact of AMR on personal health and that of their family (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim5_scenario2)
print(odds_ratio_resdim5_scenario2)

# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim5_scenario3 <- df[df$RESDIM5 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim5_scenario3$Age_Group <- ifelse(df_filtered_resdim5_scenario3$AGE %in% c(1, 2), "18-34", "35+")
df_filtered_resdim5_scenario3$Disagree_Neither <- df_filtered_resdim5_scenario3$RESDIM5 %in% c(1, 2)
table_resdim5_scenario3 <- table(df_filtered_resdim5_scenario3$Disagree_Neither, df_filtered_resdim5_scenario3$Age_Group)
rownames(table_resdim5_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_resdim5_scenario3) <- c("18-34", "35+")
chi_result_resdim5_scenario3 <- chisq.test(table_resdim5_scenario3)
odds_ratio_resdim5_scenario3 <- oddsratio(table_resdim5_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim5_scenario3, caption = "Contingency Table: Age vs. Impact of AMR on personal health and that of their family (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_resdim5_scenario3)
print(odds_ratio_resdim5_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM6= I am not at risk of getting an antibiotic-resistant infection, as long as I take my antibiotics correctly
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Agree vs. Strongly Disagree
df_filtered_resdim6_scenario1 <- df[df$RESDIM6 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim6_scenario1$Age_Group <- ifelse(df_filtered_resdim6_scenario1$AGE %in% c(1, 2), "18-34", "35+")
table_resdim6_scenario1 <- table(df_filtered_resdim6_scenario1$RESDIM6, df_filtered_resdim6_scenario1$Age_Group)
rownames(table_resdim6_scenario1) <- c("Strongly Agree", "Strongly Disagree")
colnames(table_resdim6_scenario1) <- c("18-34", "35+")
chi_result_resdim6_scenario1 <- chisq.test(table_resdim6_scenario1)
odds_ratio_resdim6_scenario1 <- oddsratio(table_resdim6_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim6_scenario1, caption = "Contingency Table: Age vs. Perception of Risk of Antibiotic-Resistant Infection (Strongly Disagree vs. Strongly Agree)"))
print(chi_result_resdim6_scenario1)
print(odds_ratio_resdim6_scenario1)
print(table_resdim6_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim6_scenario2 <- df[df$RESDIM6 %in% c(1, 2) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim6_scenario2$Age_Group <- ifelse(df_filtered_resdim6_scenario2$AGE %in% c(1, 2), "18-34", "35+")
table_resdim6_scenario2 <- table(df_filtered_resdim6_scenario2$RESDIM6, df_filtered_resdim6_scenario2$Age_Group)
rownames(table_resdim6_scenario2) <- c("Strongly Disagree", "Neither Agree Nor Disagree")
colnames(table_resdim6_scenario2) <- c("18-34", "35+")
chi_result_resdim6_scenario2 <- chisq.test(table_resdim6_scenario2)
odds_ratio_resdim6_scenario2 <- oddsratio(table_resdim6_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim6_scenario2, caption = "Contingency Table: Age vs. Perception of Risk of Antibiotic-Resistant Infection (Strongly Disagree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim6_scenario2)
print(odds_ratio_resdim6_scenario2)

# Scenario 3: Strongly Agree + Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim6_scenario3 <- df[df$RESDIM6 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim6_scenario3$Age_Group <- ifelse(df_filtered_resdim6_scenario3$AGE %in% c(1, 2), "18-34", "35+")
df_filtered_resdim6_scenario3$Agree_Neither <- df_filtered_resdim6_scenario3$RESDIM6 %in% c(2, 3)
table_resdim6_scenario3 <- table(df_filtered_resdim6_scenario3$Agree_Neither, df_filtered_resdim6_scenario3$Age_Group)
rownames(table_resdim6_scenario3) <- c("Strongly Disagree", "Strongly Agree + Neither")
colnames(table_resdim6_scenario3) <- c("18-34", "35+")
chi_result_resdim6_scenario3 <- chisq.test(table_resdim6_scenario3)
odds_ratio_resdim6_scenario3 <- oddsratio(table_resdim6_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim6_scenario3, caption = "Contingency Table: Age vs. Perception of Risk of Antibiotic-Resistant Infection (Strongly Disagree vs. Strongly Agree + Neither Agree Nor Disagree)"))
print(chi_result_resdim6_scenario3)
print(odds_ratio_resdim6_scenario3)


###############################################  35-54 vs. Other ###############################################

###CUSIN1 (I wash my hands before cooking (No= 9.4%))

# Load the Database_simplified dataframe
Database_simplified <- read_excel("C:/Database_simplified.xlsx")

# Filter the DataFrame
df_filtered <- Database_simplified[Database_simplified$CUSIN1 %in% c(0, 1) & Database_simplified$AGE %in% c(1, 2, 3, 4, 5, 6), ]

# Create a new variable for age categorization
df_filtered$Age_Group <- ifelse(df_filtered$AGE %in% c(3, 4), "35-54", "Other")

# Create the Contingency Table
table <- table(df_filtered$CUSIN1, df_filtered$Age_Group)

# Add descriptive labels
rownames(table) <- c("CUSIN1 (Yes)", "CUSIN1 (No)")
colnames(table) <- c("35-54", "Other")

# Print the contingency table using knitr
kable(table, caption = "Contingency Table: Age Group vs. Hand Washing")

# Chi-Square Test
chi_result <- chisq.test(table)

# Print the results of the Chi-Square Test
print(chi_result)

# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])

# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure

# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

---------------------------------------------------------------------------------------------------
  
  ##CUSIN2 (After handling raw food (meat and vegetables), I wash my hands with soap (No= 15.1%)
  
  df_filtered <- Database_simplified[Database_simplified$CUSIN2 %in% c(0, 1) & Database_simplified$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered$Age_Group <- ifelse(df_filtered$AGE %in% c(3, 4), "35-54", "Other")
table <- table(df_filtered$CUSIN2, df_filtered$Age_Group)
rownames(table) <- c("CUSIN2 (Yes)", "CUSIN2 (No)")
colnames(table) <- c("35-54", "Other")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: AGE vs. After handling raw food (meat and vegetables), I wash my hands with soap")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN3 (I use the same kitchen utensils for handling raw and ready-to-eat foods (Yes=25.8%))
  
  df_filtered <- Database_simplified[Database_simplified$CUSIN3 %in% c(0, 1) & Database_simplified$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered$Age_Group <- ifelse(df_filtered$AGE %in% c(3, 4), "35-54", "Other")
table <- table(df_filtered$CUSIN3, df_filtered$Age_Group)
rownames(table) <- c("CUSIN3 (Yes)", "CUSIN3 (No)")
colnames(table) <- c("18-34", "35+")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: AGE vs. I use the same kitchen utensils for handling raw and ready-to-eat foods")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

-------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN4 (I wash kitchen utensils that have been used for raw food before using them to prepare other foods  (No=16.8%))
  
  df_filtered <- Database_simplified[Database_simplified$CUSIN4 %in% c(0, 1) & Database_simplified$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered$Age_Group <- ifelse(df_filtered$AGE %in% c(3, 4), "35-54", "Other")
table <- table(df_filtered$CUSIN4, df_filtered$Age_Group)
rownames(table) <- c("CUSIN4 (Yes)", "CUSIN4 (No)")
colnames(table) <- c("35-54", "Other")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Age vs. I wash kitchen utensils that have been used for raw food before using them to prepare other foods")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

-------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN5 (I wash fruits and vegetables before eating them (No=20.7%))
  
  df_filtered <- Database_simplified[Database_simplified$CUSIN5 %in% c(0, 1) & Database_simplified$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered$Age_Group <- ifelse(df_filtered$AGE %in% c(3, 4), "35-54", "Other")
table <- table(df_filtered$CUSIN5, df_filtered$Age_Group)
rownames(table) <- c("CUSIN5 (Yes)", "CUSIN5 (No)")
colnames(table) <- c("35-54", "Other")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Age vs. I wash fruits and vegetables before eating them")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

-------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN6 (I wash my hands before eating (No=21.5))
  
  df_filtered <- Database_simplified[Database_simplified$CUSIN6 %in% c(0, 1) & Database_simplified$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered$Age_Group <- ifelse(df_filtered$AGE %in% c(3, 4), "35-54", "Other")
table <- table(df_filtered$CUSIN6, df_filtered$Age_Group)
rownames(table) <- c("CUSIN6 (Yes)", "CUSIN6 (No)")
colnames(table) <- c("35-54", "Other")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Age vs. I wash my hands before eating")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

---------------------------------------------------------------------------------------------------------------------
  
  ##PRESCATB1 When you get a prescription for antibiotics, do you follow the recommended 
  ##length of treatment and daily dosage? (No=4.2%) (Sometimes=9.6%) (No+Sometimes=13.8%)
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
df <- Database_simplified
############### 1st scenario= No
df_filtered_prescatb1 <- df[df$PRESCATB1 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_prescatb1$Age_Group <- ifelse(df_filtered_prescatb1$AGE %in% c(3, 4), "35-54", "Other")
table_prescatb1 <- table(df_filtered_prescatb1$PRESCATB1, df_filtered_prescatb1$Age_Group)
# Add descriptive labels to the rows and columns
rownames(table_prescatb1) <- c("Yes", "No")
# Perform the Chi-Squared test
chi_result_prescatb1 <- chisq.test(table_prescatb1)
# Calculate the odds ratio and confidence interval
odds_ratio_prescatb1 <- oddsratio(table_prescatb1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_prescatb1, caption = "Contingency Table: Age vs. Following Prescription for Antibiotics"))
# Print the results of the Chi-Squared test
print(chi_result_prescatb1)
# Print the odds ratio and confidence interval
print(odds_ratio_prescatb1)

################## 2nd scenario= Sometimes
df_filtered_prescatb1_sometimes <- df[df$PRESCATB1 %in% c(0, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_prescatb1_sometimes$Age_Group <- ifelse(df_filtered_prescatb1_sometimes$AGE %in% c(3, 4), "35-54", "Other")
table_prescatb1_sometimes <- table(df_filtered_prescatb1_sometimes$PRESCATB1, df_filtered_prescatb1_sometimes$Age_Group)
# Add descriptive labels to the rows and columns
rownames(table_prescatb1_sometimes) <- c("Yes", "No")
# Perform the Chi-Squared test
chi_result_prescatb1_sometimes <- chisq.test(table_prescatb1_sometimes)
# Calculate the odds ratio and confidence interval
odds_ratio_prescatb1_sometimes <- oddsratio(table_prescatb1_sometimes, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_prescatb1_sometimes, caption = "Contingency Table: Age vs. Following Prescription for Antibiotics Sometimes"))
# Print the results of the Chi-Squared test
print(chi_result_prescatb1_sometimes)
# Print the odds ratio and confidence interval
print(odds_ratio_prescatb1_sometimes)

################## 3rd scenario= No+Sometimes
# Filter for 'Yes', 'No', and 'Sometimes' responses for PRESCATB1 and genders 'Female' and 'Male'
df_filtered_prescatb1_combined <- df[df$PRESCATB1 %in% c(0, 1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_prescatb1_combined$Age_Group <- ifelse(df_filtered_prescatb1_combined$AGE %in% c(3, 4), "35-54", "Other")
df_filtered_prescatb1_combined$No_Sometimes <- df_filtered_prescatb1_combined$PRESCATB1 %in% c(1, 3)
table_prescatb1_combined <- table(df_filtered_prescatb1_combined$No_Sometimes, df_filtered_prescatb1_combined$Age_Group)
# Adjust the table to have 'Yes' and 'No+Sometimes' as row names
rownames(table_prescatb1_combined) <- c("Yes", "No_Sometimes")
# Perform the Chi-Squared test
chi_result_prescatb1_combined <- chisq.test(table_prescatb1_combined)
# Calculate the odds ratio and confidence interval
odds_ratio_prescatb1_combined <- oddsratio(table_prescatb1_combined, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_prescatb1_combined, caption = "Contingency Table: Age vs. Following Prescription for Antibiotics (Yes vs. No+Sometimes)"))
# Print the results of the Chi-Squared test
print(chi_result_prescatb1_combined)
# Print the odds ratio and confidence interval
print(odds_ratio_prescatb1_combined)

---------------------------------------------------------------------------------------------------------------------
  
  ##ARRETATB Do you stop taking antibiotics when symptoms start to disappear?
  ##(Always=7.3%) (Sometimes=20.4%) (Always+Sometimes=27.7%)
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
df <- Database_simplified
############### 1st scenario= Always
df_filtered_arretatb <- df[df$ARRETATB %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_arretatb$Age_Group <- ifelse(df_filtered_arretatb$AGE %in% c(3, 4), "35-54", "Other")
table_arretatb <- table(df_filtered_arretatb$ARRETATB, df_filtered_arretatb$Age_Group)
# Add descriptive labels to the rows and columns
rownames(table_arretatb) <- c("Always", "Never")
# Perform the Chi-Squared test
chi_result_arretatb <- chisq.test(table_arretatb)
# Calculate the odds ratio and confidence interval
odds_ratio_arretatb <- oddsratio(table_arretatb, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_arretatb, caption = "Contingency Table: Age vs. Stopping Antibiotics Always vs. Never"))
# Print the results of the Chi-Squared test
print(chi_result_arretatb)
# Print the odds ratio and confidence interval
print(odds_ratio_arretatb)

################# 2nd Cenario: Sometimes
df_filtered_arretatb_sometimes <- df[df$ARRETATB %in% c(1, 2) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_arretatb_sometimes$Age_Group <- ifelse(df_filtered_arretatb_sometimes$AGE %in% c(3, 4), "35-54", "Other")
table_arretatb_sometimes <- table(df_filtered_arretatb_sometimes$ARRETATB == 2, df_filtered_arretatb_sometimes$Age_Group)
# Add descriptive labels to the rows and columns
rownames(table_arretatb_sometimes) <- c("Never", "Sometimes")
# Perform the Chi-Squared test
chi_result_arretatb_sometimes <- chisq.test(table_arretatb_sometimes)
# Calculate the odds ratio and confidence interval
odds_ratio_arretatb_sometimes <- oddsratio(table_arretatb_sometimes, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_arretatb_sometimes, caption = "Contingency Table: Age vs. Stopping Antibiotics Sometimes vs. Never"))
# Print the results of the Chi-Squared test
print(chi_result_arretatb_sometimes)
# Print the odds ratio and confidence interval
print(odds_ratio_arretatb_sometimes)

############### #3rd scenario= Sometimes+Always
df_filtered_arretatb_combined <- df[df$ARRETATB %in% c(0, 1, 2) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_arretatb_combined$Age_Group <- ifelse(df_filtered_arretatb_combined$AGE %in% c(3, 4), "35-54", "Other")
df_filtered_arretatb_combined$Sometimes_Always <- df_filtered_arretatb_combined$ARRETATB %in% c(0, 2)
table_arretatb_combined <- table(df_filtered_arretatb_combined$Sometimes_Always, df_filtered_arretatb_combined$Age_Group)
# Add descriptive labels to the rows and columns
rownames(table_arretatb_combined) <- c("Never", "Sometimes_Always")
# Perform the Chi-Squared test
chi_result_arretatb_combined <- chisq.test(table_arretatb_combined)
# Calculate the odds ratio and confidence interval
odds_ratio_arretatb_combined <- oddsratio(table_arretatb_combined, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_arretatb_combined, caption = "Contingency Table: Age vs. Stopping Antibiotics (Sometimes+Always vs. Never)"))
# Print the results of the Chi-Squared test
print(chi_result_arretatb_combined)
# Print the odds ratio and confidence interval
print(odds_ratio_arretatb_combined)

---------------------------------------------------------------------------------------------------------------------
  
  ##ATBORAL1 Have you ever taken an oral antibiotic treatment (by mouth) without a medical prescription? (Yes=12.3%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
df <- Database_simplified  
df_filtered_atboral <- df[df$ATBORAL1 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atboral$Age_Group <- ifelse(df_filtered_atboral$AGE %in% c(3, 4), "35-54", "Other")
table_atboral <- table(df_filtered_atboral$ATBORAL1, df_filtered_atboral$Age_Group)
# Add descriptive labels to the rows and columns
rownames(table_atboral) <- c("Yes", "No")
# Perform the Chi-Squared test
chi_result_atboral <- chisq.test(table_atboral)
# Calculate the odds ratio and confidence interval
odds_ratio_atboral <- oddsratio(table_atboral, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atboral, caption = "Contingency Table: Age vs. Taking Oral Antibiotics Without Prescription (Yes vs. No)"))
# Print the results of the Chi-Squared test
print(chi_result_atboral)
# Print the odds ratio and confidence interval
print(odds_ratio_atboral)

--------------------------------------------------------------------------------------------------------
  
  ### ATBANI1 I can exchange resistant bacteria with my pet (False=23.2%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
df <- Database_simplified  
df_filtered_atbani1 <- df[df$ATBANI1 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbani1$Age_Group <- ifelse(df_filtered_atbani1$AGE %in% c(3, 4), "35-54", "Other")
table_atbani1 <- table(df_filtered_atbani1$ATBANI1, df_filtered_atbani1$Age_Group)
rownames(table_atbani1) <- c("True", "False")
colnames(table_atbani1) <- c("35-54", "Other")
# Perform the Chi-Squared test
chi_result_atbani1 <- chisq.test(table_atbani1)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani1 <- oddsratio(table_atbani1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani1, caption = "Contingency Table: Age vs. Exchanging Resistant Bacteria with Pets (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani1)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani1)

---------------------------------------------------------------------------------------------------------------------
  
  ### ATBANI2=The use of antibiotics in livestock and crops can increase the 
  #presence of resistant bacteria in the environment (False=14.7%)
  
  df_filtered_atbani2 <- df[df$ATBANI2 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbani2$Age_Group <- ifelse(df_filtered_atbani2$AGE %in% c(3, 4), "35-54", "Other")
table_atbani2 <- table(df_filtered_atbani2$ATBANI2, df_filtered_atbani2$Age_Group)
rownames(table_atbani2) <- c("True", "False")
colnames(table_atbani2) <- c("35-54", "Other")
# Perform the Chi-Squared test
chi_result_atbani2 <- chisq.test(table_atbani2)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani2 <- oddsratio(table_atbani2, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani2, caption = "Contingency Table: Age vs. Antibiotics in Livestock and Crops Affecting Environment (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani2)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani2)


--------------------------------------------------------------------------------------------------------------------
  
  ##### ATBANI3	The use of antibiotics in livestock and crops can affect me directly
  ##(I can get resistant bacteria in my body) (False=26.3%)
  
  df_filtered_atbani3 <- df[df$ATBANI3 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbani3$Age_Group <- ifelse(df_filtered_atbani3$AGE %in% c(3, 4), "35-54", "Other")
table_atbani3 <- table(df_filtered_atbani3$ATBANI3, df_filtered_atbani3$Age_Group)
rownames(table_atbani3) <- c("True", "False")
colnames(table_atbani3) <- c("35-54", "Other")
# Perform the Chi-Squared test
chi_result_atbani3 <- chisq.test(table_atbani3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani3 <- oddsratio(table_atbani3, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani3, caption = "Contingency Table: Age vs. Antibiotics in Livestock and Crops Affecting Humans Directly (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani3)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani3)

-------------------------------------------------------------------------------------------------------------------
  ##### ATBANI4	Resistant bacteria are only found in hospitals (True=10.8%)
  
  df_filtered_atbani4 <- df[df$ATBANI4 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbani4$Age_Group <- ifelse(df_filtered_atbani4$AGE %in% c(3, 4), "35-54", "Other")
table_atbani4 <- table(df_filtered_atbani4$ATBANI4, df_filtered_atbani4$Age_Group)
rownames(table_atbani4) <- c("True", "False")
colnames(table_atbani4) <- c("35-54", "Other")
# Perform the Chi-Squared test
chi_result_atbani4 <- chisq.test(table_atbani4)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani4 <- oddsratio(table_atbani4, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani4, caption = "Contingency Table: Age vs. Resistant Bacteria Found Only in Hospitals (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani4)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani4)

----------------------------------------------------------------------------------------------------------------------
  
  #####RESATB1	Antibiotic resistance occurs when your body becomes resistant to antibiotics and they
  ##no longer work as well (True=58.3%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
df <- Database_simplified   
df_filtered_resatb1 <- df[df$RESATB1 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb1$Age_Group <- ifelse(df_filtered_resatb1$AGE %in% c(3, 4), "35-54", "Other")
table_resatb1 <- table(df_filtered_resatb1$RESATB1, df_filtered_resatb1$Age_Group)
rownames(table_resatb1) <- c("True", "False")
colnames(table_resatb1) <- c("35-54", "Other")
# Perform the Chi-Squared test
chi_result_resatb1 <- chisq.test(table_resatb1)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb1 <- oddsratio(table_resatb1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb1, caption = "Contingency Table: Age vs. Understanding of Antibiotic Resistance (RESATB1: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb1)
print(odds_ratio_resatb1)

-------------------------------------------------------------------------------------------------------------------
  
  #####RESATB2	Many infections are becoming increasingly resistant to antibiotic treatment  (False=12.5%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb2 <- df[df$RESATB2 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb2$Age_Group <- ifelse(df_filtered_resatb2$AGE %in% c(3, 4), "35-54", "Other")
table_resatb2 <- table(df_filtered_resatb2$RESATB2, df_filtered_resatb2$Age_Group)
rownames(table_resatb2) <- c("True", "False")
colnames(table_resatb2) <- c("35-54", "Other")
# Perform the Chi-Squared test
chi_result_resatb2 <- chisq.test(table_resatb2)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb2 <- oddsratio(table_resatb2, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb2, caption = "Contingency Table: Age vs. Perception of Increasing Infection Resistance (RESATB2: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb2)
print(odds_ratio_resatb2)

---------------------------------------------------------------------------------------------------------------------
  #####RESATB3	If bacteria are resistant to antibiotics, it can be very difficult or impossible to treat the infections they cause (False=16.7%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb3 <- df[df$RESATB3 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb3$Age_Group <- ifelse(df_filtered_resatb3$AGE %in% c(3, 4), "35-54", "Other")
table_resatb3 <- table(df_filtered_resatb3$RESATB3, df_filtered_resatb3$Age_Group)
rownames(table_resatb3) <- c("True", "False")
colnames(table_resatb3) <- c("35-54", "Other")
# Perform the Chi-Squared test
chi_result_resatb3 <- chisq.test(table_resatb3)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb3 <- oddsratio(table_resatb3, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb3, caption = "Contingency Table: Age vs. Perception of Difficulty Treating Infections (RESATB3: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb3)
print(odds_ratio_resatb3)
----------------------------------------------------------------------------------------------------------------------
  #####RESATB4	Antibiotic resistance is an issue that could affect me or my family (False=11.8%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb4 <- df[df$RESATB4 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb4$Age_Group <- ifelse(df_filtered_resatb4$AGE %in% c(3, 4), "35-54", "Other")
table_resatb4 <- table(df_filtered_resatb4$RESATB4, df_filtered_resatb4$Age_Group)
rownames(table_resatb4) <- c("True", "False")
colnames(table_resatb4) <- c("35-54", "Other")
# Perform the Chi-Squared test
chi_result_resatb4 <- chisq.test(table_resatb4)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb4 <- oddsratio(table_resatb4, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb4, caption = "Contingency Table: Age vs. Perception of Antibiotic Resistance Affecting One's Family (RESATB4: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb4)
print(odds_ratio_resatb4)

---------------------------------------------------------------------------------------------------------------------
  #####RESATB5	Antibiotic resistance is an issue in other countries but not here (True=9.9%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb5 <- df[df$RESATB5 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb5$Age_Group <- ifelse(df_filtered_resatb5$AGE %in% c(3, 4), "35-54", "Other")
table_resatb5 <- table(df_filtered_resatb5$RESATB5, df_filtered_resatb5$Age_Group)
rownames(table_resatb5) <- c("True", "False")
colnames(table_resatb5) <- c("35-54", "Other")
# Perform the Chi-Squared test
chi_result_resatb5 <- chisq.test(table_resatb5)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb5 <- oddsratio(table_resatb5, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb5, caption = "Contingency Table: Age vs. Perception of Antibiotic Resistance as an Issue Only in Other Countries (RESATB5: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb5)
print(odds_ratio_resatb5)
---------------------------------------------------------------------------------------------------------------------  
  
  #####RESATB6	Antibiotic resistance is only a problem for people who take antibiotics regularly (True=17.5%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb6 <- df[df$RESATB6 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb6$Age_Group <- ifelse(df_filtered_resatb6$AGE %in% c(3, 4), "35-54", "Other")
table_resatb6 <- table(df_filtered_resatb6$RESATB6, df_filtered_resatb6$Age_Group)
rownames(table_resatb6) <- c("True", "False")
colnames(table_resatb6) <- c("35-54", "Other")
# Perform the Chi-Squared test
chi_result_resatb6 <- chisq.test(table_resatb6)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb6 <- oddsratio(table_resatb6, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb6, caption = "Contingency Table: Age vs. Perception of Antibiotic Resistance as a Problem Only for Regular Antibiotic Users (RESATB6: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb6)
print(odds_ratio_resatb6)

--------------------------------------------------------------------------------------------------------------------- 
  #####RESATB7	Bacteria that are resistant to antibiotics can be spread from person to person (False=20.2%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb7 <- df[df$RESATB7 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb7$Age_Group <- ifelse(df_filtered_resatb7$AGE %in% c(3, 4), "35-54", "Other")
table_resatb7 <- table(df_filtered_resatb7$RESATB7, df_filtered_resatb7$Age_Group)
rownames(table_resatb7) <- c("True", "False")
colnames(table_resatb7) <- c("35-54", "Other")
# Perform the Chi-Squared test
chi_result_resatb7 <- chisq.test(table_resatb7)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb7 <- oddsratio(table_resatb7, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb7, caption = "Contingency Table: Age vs. Perception of Bacteria Transmission Person to Person (RESATB7: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb7)
print(odds_ratio_resatb7)

--------------------------------------------------------------------------------------------------------------------
  #####RESATB8	Antibiotic-resistant infections could make medical procedures like surgery, organ transplants,
  ##and cancer treatment much more dangerous (False=12.0%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb8 <- df[df$RESATB8 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb8$Age_Group <- ifelse(df_filtered_resatb8$AGE %in% c(3, 4), "35-54", "Other")
table_resatb8 <- table(df_filtered_resatb8$RESATB8, df_filtered_resatb8$Age_Group)
rownames(table_resatb8) <- c("True", "False")
colnames(table_resatb8) <- c("35-54", "Other")
# Perform the Chi-Squared test
chi_result_resatb8 <- chisq.test(table_resatb8)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb8 <- oddsratio(table_resatb8, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb8, caption = "Contingency Table: Age vs. Perception of Antibiotic-Resistant Infections and Medical Procedures (RESATB8: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb8)
print(odds_ratio_resatb8)

--------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL1	Farmers should give fewer antibiotics to food-producing animals 
  
  ##################### 1st scenario (Strongly desagree=8.68%) vs. Strongly Agree
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl1_scenario1 <- df[df$ATBRGL1 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl1_scenario1$Age_Group <- ifelse(df_filtered_atbrgl1_scenario1$AGE %in% c(3, 4), "35-54", "Other")
table_atbrgl1_scenario1 <- table(df_filtered_atbrgl1_scenario1$ATBRGL1, df_filtered_atbrgl1_scenario1$Age_Group)
rownames(table_atbrgl1_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl1_scenario1) <- c("35-54", "Other")
# Perform the Chi-Squared test
chi_result_atbrgl1_scenario1 <- chisq.test(table_atbrgl1_scenario1)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl1_scenario1 <- oddsratio(table_atbrgl1_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl1_scenario1, caption = "Contingency Table: Age vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_atbrgl1_scenario1)
print(odds_ratio_atbrgl1_scenario1)

############################# 2nd scenario Farmers should give fewer antibiotics to
##food-producing animals (Neither agree nor desagree=22.6%) vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl1_scenario2 <- df[df$ATBRGL1 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl1_scenario2$Age_Group <- ifelse(df_filtered_atbrgl1_scenario2$AGE %in% c(3, 4), "35-54", "Other")
table_atbrgl1_scenario2 <- table(df_filtered_atbrgl1_scenario2$ATBRGL1, df_filtered_atbrgl1_scenario2$Age_Group)
rownames(table_atbrgl1_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl1_scenario2) <- c("35-54", "Other")
# Perform the Chi-Squared test
chi_result_atbrgl1_scenario2 <- chisq.test(table_atbrgl1_scenario2)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl1_scenario2 <- oddsratio(table_atbrgl1_scenario2, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl1_scenario2, caption = "Contingency Table: Age vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Neither Agree Nor Disagree)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_atbrgl1_scenario2)
print(odds_ratio_atbrgl1_scenario2)

############################# 3rd scenario (Strongly desagree + Neither agree nor desagree=31.28%) vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl1_scenario3 <- df[df$ATBRGL1 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl1_scenario3$Age_Group <- ifelse(df_filtered_atbrgl1_scenario3$AGE %in% c(3, 4), "35-54", "Other")
df_filtered_atbrgl1_scenario3$Disagree_Neither <- df_filtered_atbrgl1_scenario3$ATBRGL1 %in% c(1, 2)
table_atbrgl1_scenario3 <- table(df_filtered_atbrgl1_scenario3$Disagree_Neither, df_filtered_atbrgl1_scenario3$Age_Group)
rownames(table_atbrgl1_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl1_scenario3) <- c("35-54", "Other")
# Perform the Chi-Squared test
chi_result_atbrgl1_scenario3 <- chisq.test(table_atbrgl1_scenario3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl1_scenario3 <- oddsratio(table_atbrgl1_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl1_scenario3, caption = "Contingency Table: Age vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree + Neither)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_atbrgl1_scenario3)
print(odds_ratio_atbrgl1_scenario3)

--------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL2	People should not keep antibiotics and use them later for other illnesses  
  
  ############################# 1st scenario Strongly desagree vs. Strongly Agree
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the database
df <- Database_simplified
## Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_atbrgl2_scenario1 <- df[df$ATBRGL2 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl2_scenario1$Age_Group <- ifelse(df_filtered_atbrgl2_scenario1$AGE %in% c(3, 4), "35-54", "Other")
table_atbrgl2_scenario1 <- table(df_filtered_atbrgl2_scenario1$ATBRGL2, df_filtered_atbrgl2_scenario1$Age_Group)
rownames(table_atbrgl2_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl2_scenario1) <- c("35-54", "Other")
# Perform Chi-Squared test
chi_result_atbrgl2_scenario1 <- chisq.test(table_atbrgl2_scenario1)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl2_scenario1 <- oddsratio(table_atbrgl2_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl2_scenario1, caption = "Contingency Table: Age vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl2_scenario1)
print(odds_ratio_atbrgl2_scenario1)

############################# 2nd scenario Neither agree nor desagree vs. Strongly Agree
# Filter for 'Strongly Agree' (3) and 'Neither Agree Nor Disagree' (2) responses for ATBRGL2
df_filtered_atbrgl2_scenario2 <- df[df$ATBRGL2 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl2_scenario2$Age_Group <- ifelse(df_filtered_atbrgl2_scenario2$AGE %in% c(3, 4), "35-54", "Other")
table_atbrgl2_scenario2 <- table(df_filtered_atbrgl2_scenario2$ATBRGL2, df_filtered_atbrgl2_scenario2$Age_Group)
rownames(table_atbrgl2_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl2_scenario2) <- c("35-54", "Other")
# Perform Chi-Squared test
chi_result_atbrgl2_scenario2 <- chisq.test(table_atbrgl2_scenario2)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl2_scenario2 <- oddsratio(table_atbrgl2_scenario2, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl2_scenario2, caption = "Contingency Table: Age vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl2_scenario2)
print(odds_ratio_atbrgl2_scenario2)


############################# 3rd scenario Neither agree nor desagree + Stringly Disagree vs. Strongly Agree
df_filtered_atbrgl2_scenario3 <- df[df$ATBRGL2 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl2_scenario3$Age_Group <- ifelse(df_filtered_atbrgl2_scenario3$AGE %in% c(3, 4), "35-54", "Other")
df_filtered_atbrgl2_scenario3$Disagree_Neither <- df_filtered_atbrgl2_scenario3$ATBRGL2 %in% c(1, 2)
table_atbrgl2_scenario3 <- table(df_filtered_atbrgl2_scenario3$Disagree_Neither, df_filtered_atbrgl2_scenario3$Age_Group)
rownames(table_atbrgl2_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl2_scenario3) <- c("35-54", "Other")
# Perform the Chi-Squared test
chi_result_atbrgl2_scenario3 <- chisq.test(table_atbrgl2_scenario3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl2_scenario3 <- oddsratio(table_atbrgl2_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl2_scenario3, caption = "Contingency Table: Age vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl2_scenario3)
print(odds_ratio_atbrgl2_scenario3)

--------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL3 Parents should make sure all of their children’s vaccinations are up-to-date 
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)

####1st scenario
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl3_scenario1 <- df[df$ATBRGL3 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl3_scenario1$Age_Group <- ifelse(df_filtered_atbrgl3_scenario1$AGE %in% c(3, 4), "35-54", "Other")
table_atbrgl3_scenario1 <- table(df_filtered_atbrgl3_scenario1$ATBRGL3, df_filtered_atbrgl3_scenario1$Age_Group)
rownames(table_atbrgl3_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl3_scenario1) <- c("35-54", "Other")
# Perform Chi-Squared test
chi_result_atbrgl3_scenario1 <- chisq.test(table_atbrgl3_scenario1)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl3_scenario1 <- oddsratio(table_atbrgl3_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl3_scenario1, caption = "Contingency Table: Age vs. Opinion on Children's Vaccinations (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl3_scenario1)
print(odds_ratio_atbrgl3_scenario1)

### 2nd Scenario
df_filtered_atbrgl3_scenario2 <- df[df$ATBRGL3 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl3_scenario2$Age_Group <- ifelse(df_filtered_atbrgl3_scenario2$AGE %in% c(3, 4), "35-54", "Other")
table_atbrgl3_scenario2 <- table(df_filtered_atbrgl3_scenario2$ATBRGL3, df_filtered_atbrgl3_scenario2$Age_Group)
rownames(table_atbrgl3_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl3_scenario2) <- c("35-54", "Other")
# Perform Chi-Squared test
chi_result_atbrgl3_scenario2 <- chisq.test(table_atbrgl3_scenario2)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl3_scenario2 <- oddsratio(table_atbrgl3_scenario2, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl3_scenario2, caption = "Contingency Table: Age vs. Opinion on Children's Vaccinations (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl3_scenario2)
print(odds_ratio_atbrgl3_scenario2)

## 3rd scenario
df_filtered_atbrgl3_scenario3 <- df[df$ATBRGL3 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl3_scenario3$Age_Group <- ifelse(df_filtered_atbrgl3_scenario3$AGE %in% c(3, 4), "35-54", "Other")
df_filtered_atbrgl3_scenario3$Disagree_Neither <- df_filtered_atbrgl3_scenario3$ATBRGL3 %in% c(1, 2)
table_atbrgl3_scenario3 <- table(df_filtered_atbrgl3_scenario3$Disagree_Neither, df_filtered_atbrgl3_scenario3$Age_Group)
rownames(table_atbrgl3_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl3_scenario3) <- c("35-54", "Other")
# Perform the Chi-Squared test
chi_result_atbrgl3_scenario3 <- chisq.test(table_atbrgl3_scenario3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl3_scenario3 <- oddsratio(table_atbrgl3_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl3_scenario3, caption = "Contingency Table: Age vs. Opinion on Children's Vaccinations (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl3_scenario3)
print(odds_ratio_atbrgl3_scenario3)

---------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL4 People should wash their hands regularly
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

## Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_atbrgl4_scenario1 <- df[df$ATBRGL4 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl4_scenario1$Age_Group <- ifelse(df_filtered_atbrgl4_scenario1$AGE %in% c(3, 4), "35-54", "Other")
table_atbrgl4_scenario1 <- table(df_filtered_atbrgl4_scenario1$ATBRGL4, df_filtered_atbrgl4_scenario1$Age_Group)
rownames(table_atbrgl4_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl4_scenario1) <- c("35-54", "Other")
chi_result_atbrgl4_scenario1 <- chisq.test(table_atbrgl4_scenario1)
odds_ratio_atbrgl4_scenario1 <- oddsratio(table_atbrgl4_scenario1, conf.level = 0.95)$measure
print(kable(table_atbrgl4_scenario1, caption = "Contingency Table: Age vs. Hand Washing Importance (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl4_scenario1)
print(odds_ratio_atbrgl4_scenario1)

## Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl4_scenario2 <- df[df$ATBRGL4 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl4_scenario2$Age_Group <- ifelse(df_filtered_atbrgl4_scenario2$AGE %in% c(3, 4), "35-54", "Other")
table_atbrgl4_scenario2 <- table(df_filtered_atbrgl4_scenario2$ATBRGL4, df_filtered_atbrgl4_scenario2$Age_Group)
rownames(table_atbrgl4_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl4_scenario2) <- c("35-54", "Other")
chi_result_atbrgl4_scenario2 <- chisq.test(table_atbrgl4_scenario2)
odds_ratio_atbrgl4_scenario2 <- oddsratio(table_atbrgl4_scenario2, conf.level = 0.95)$measure
print(kable(table_atbrgl4_scenario2, caption = "Contingency Table: Age vs. Hand Washing Importance (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl4_scenario2)
print(odds_ratio_atbrgl4_scenario2)

## Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl4_scenario3 <- df[df$ATBRGL4 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl4_scenario3$Age_Group <- ifelse(df_filtered_atbrgl4_scenario3$AGE %in% c(3, 4), "35-54", "Other")
df_filtered_atbrgl4_scenario3$Disagree_Neither <- df_filtered_atbrgl4_scenario3$ATBRGL4 %in% c(1, 2)
table_atbrgl4_scenario3 <- table(df_filtered_atbrgl4_scenario3$Disagree_Neither, df_filtered_atbrgl4_scenario3$Age_Group)
rownames(table_atbrgl4_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl4_scenario3) <- c("35-54", "Other")
chi_result_atbrgl4_scenario3 <- chisq.test(table_atbrgl4_scenario3)
odds_ratio_atbrgl4_scenario3 <- oddsratio(table_atbrgl4_scenario3, conf.level = 0.95)$measure
print(kable(table_atbrgl4_scenario3, caption = "Contingency Table: Age vs. Hand Washing Importance (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl4_scenario3)
print(odds_ratio_atbrgl4_scenario3)

---------------------------------------------------------------------------------------------------------------------
  
  #ATBRGL5 Doctors should only prescribe antibiotics when they are needed 
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)

# Load the Database_simplified dataframe
df <- Database_simplified

## Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_atbrgl5_scenario1 <- df[df$ATBRGL5 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl5_scenario1$Age_Group <- ifelse(df_filtered_atbrgl5_scenario1$AGE %in% c(3, 4), "35-54", "Other")
table_atbrgl5_scenario1 <- table(df_filtered_atbrgl5_scenario1$ATBRGL5, df_filtered_atbrgl5_scenario1$Age_Group)
rownames(table_atbrgl5_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl5_scenario1) <- c("35-54", "Other")
chi_result_atbrgl5_scenario1 <- chisq.test(table_atbrgl5_scenario1)
odds_ratio_atbrgl5_scenario1 <- oddsratio(table_atbrgl5_scenario1, conf.level = 0.95)$measure
print(kable(table_atbrgl5_scenario1, caption = "Contingency Table: Age vs. Antibiotic Prescription Necessity (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl5_scenario1)
print(odds_ratio_atbrgl5_scenario1)

## Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl5_scenario2 <- df[df$ATBRGL5 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl5_scenario2$Age_Group <- ifelse(df_filtered_atbrgl5_scenario2$AGE %in% c(3, 4), "35-54", "Other")
table_atbrgl5_scenario2 <- table(df_filtered_atbrgl5_scenario2$ATBRGL5, df_filtered_atbrgl5_scenario2$Age_Group)
rownames(table_atbrgl5_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl5_scenario2) <- c("35-54", "Other")
chi_result_atbrgl5_scenario2 <- chisq.test(table_atbrgl5_scenario2)
odds_ratio_atbrgl5_scenario2 <- oddsratio(table_atbrgl5_scenario2, conf.level = 0.95)$measure
print(kable(table_atbrgl5_scenario2, caption = "Contingency Table: Age vs. Antibiotic Prescription Necessity (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl5_scenario2)
print(odds_ratio_atbrgl5_scenario2)

## Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl5_scenario3 <- df[df$ATBRGL5 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl5_scenario3$Age_Group <- ifelse(df_filtered_atbrgl5_scenario3$AGE %in% c(3, 4), "35-54", "Other")
df_filtered_atbrgl5_scenario3$Disagree_Neither <- df_filtered_atbrgl5_scenario3$ATBRGL5 %in% c(1, 2)
table_atbrgl5_scenario3 <- table(df_filtered_atbrgl5_scenario3$Disagree_Neither, df_filtered_atbrgl5_scenario3$Age_Group)
rownames(table_atbrgl5_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl5_scenario3) <- c("35-54", "Other")
chi_result_atbrgl5_scenario3 <- chisq.test(table_atbrgl5_scenario3)
odds_ratio_atbrgl5_scenario3 <- oddsratio(table_atbrgl5_scenario3, conf.level = 0.95)$measure
print(kable(table_atbrgl5_scenario3, caption = "Contingency Table: Age vs. Antibiotic Prescription Necessity (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl5_scenario3)
print(odds_ratio_atbrgl5_scenario3)

----------------------------------------------------------------------------------------------------------------------
  
  ##ATBRGL6= People should only use antibiotics when prescribed by a doctor or nurse
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

## Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_atbrgl6_scenario1 <- df[df$ATBRGL6 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl6_scenario1$Age_Group <- ifelse(df_filtered_atbrgl6_scenario1$AGE %in% c(3, 4), "35-54", "Other")
table_atbrgl6_scenario1 <- table(df_filtered_atbrgl6_scenario1$ATBRGL6, df_filtered_atbrgl6_scenario1$Age_Group)
rownames(table_atbrgl6_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl6_scenario1) <- c("35-54", "Other")
chi_result_atbrgl6_scenario1 <- chisq.test(table_atbrgl6_scenario1)
odds_ratio_atbrgl6_scenario1 <- oddsratio(table_atbrgl6_scenario1, conf.level = 0.95)$measure
print(kable(table_atbrgl6_scenario1, caption = "Contingency Table: Age vs. Antibiotic only when prescribed (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl6_scenario1)
print(odds_ratio_atbrgl6_scenario1)

## Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl6_scenario2 <- df[df$ATBRGL6 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl6_scenario2$Age_Group <- ifelse(df_filtered_atbrgl6_scenario2$AGE %in% c(3, 4), "35-54", "Other")
table_atbrgl6_scenario2 <- table(df_filtered_atbrgl6_scenario2$ATBRGL6, df_filtered_atbrgl6_scenario2$Age_Group)
rownames(table_atbrgl6_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl6_scenario2) <- c("35-54", "Other")
chi_result_atbrgl6_scenario2 <- chisq.test(table_atbrgl6_scenario2)
odds_ratio_atbrgl6_scenario2 <- oddsratio(table_atbrgl6_scenario2, conf.level = 0.95)$measure
print(kable(table_atbrgl6_scenario2, caption = "Contingency Table: Age vs. Antibiotic only when prescribed (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl6_scenario2)
print(odds_ratio_atbrgl6_scenario2)

## Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl6_scenario3 <- df[df$ATBRGL6 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl6_scenario3$Age_Group <- ifelse(df_filtered_atbrgl6_scenario3$AGE %in% c(3, 4), "35-54", "Other")
df_filtered_atbrgl6_scenario3$Disagree_Neither <- df_filtered_atbrgl6_scenario3$ATBRGL6 %in% c(1, 2)
table_atbrgl6_scenario3 <- table(df_filtered_atbrgl6_scenario3$Disagree_Neither, df_filtered_atbrgl6_scenario3$Age_Group)
rownames(table_atbrgl6_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl6_scenario3) <- c("35-54", "Other")
chi_result_atbrgl6_scenario3 <- chisq.test(table_atbrgl6_scenario3)
odds_ratio_atbrgl6_scenario3 <- oddsratio(table_atbrgl6_scenario3, conf.level = 0.95)$measure
print(kable(table_atbrgl6_scenario3, caption = "Contingency Table: Age vs. Antibiotic only when prescribed (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl6_scenario3)
print(odds_ratio_atbrgl6_scenario3)

----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM1= Antibiotic resistance is one of the biggest problems the world faces
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_resdim1_scenario1 <- df[df$RESDIM1 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim1_scenario1$Age_Group <- ifelse(df_filtered_resdim1_scenario1$AGE %in% c(3, 4), "35-54", "Other")
table_resdim1_scenario1 <- table(df_filtered_resdim1_scenario1$RESDIM1, df_filtered_resdim1_scenario1$Age_Group)
rownames(table_resdim1_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim1_scenario1) <- c("35-54", "Other")
chi_result_resdim1_scenario1 <- chisq.test(table_resdim1_scenario1)
odds_ratio_resdim1_scenario1 <- oddsratio(table_resdim1_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim1_scenario1, caption = "Contingency Table: Age vs. Perception of Antibiotic Resistance as a Global Problem (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_resdim1_scenario1)
print(odds_ratio_resdim1_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim1_scenario2 <- df[df$RESDIM1 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim1_scenario2$Age_Group <- ifelse(df_filtered_resdim1_scenario2$AGE %in% c(3, 4), "35-54", "Other")
table_resdim1_scenario2 <- table(df_filtered_resdim1_scenario2$RESDIM1, df_filtered_resdim1_scenario2$Age_Group)
rownames(table_resdim1_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_resdim1_scenario2) <- c("35-54", "Other")
chi_result_resdim1_scenario2 <- chisq.test(table_resdim1_scenario2)
odds_ratio_resdim1_scenario2 <- oddsratio(table_resdim1_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim1_scenario2, caption = "Contingency Table: Age vs. Perception of Antibiotic Resistance as a Global Problem (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim1_scenario2)
print(odds_ratio_resdim1_scenario2)

# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim1_scenario3 <- df[df$RESDIM1 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim1_scenario3$Age_Group <- ifelse(df_filtered_resdim1_scenario3$AGE %in% c(3, 4), "35-54", "Other")
df_filtered_resdim1_scenario3$Disagree_Neither <- df_filtered_resdim1_scenario3$RESDIM1 %in% c(1, 2)
table_resdim1_scenario3 <- table(df_filtered_resdim1_scenario3$Disagree_Neither, df_filtered_resdim1_scenario3$Age_Group)
rownames(table_resdim1_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_resdim1_scenario3) <- c("35-54", "Other")
chi_result_resdim1_scenario3 <- chisq.test(table_resdim1_scenario3)
odds_ratio_resdim1_scenario3 <- oddsratio(table_resdim1_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim1_scenario3, caption = "Contingency Table: Age vs. Perception of Antibiotic Resistance as a Global Problem (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_resdim1_scenario3)
print(odds_ratio_resdim1_scenario3)

----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM2= Medical experts will solve the problem of antibiotic resistance before it becomes too serious 
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Load the Database_simplified dataframe
df <- read_excel("C:/Database_simplified.xlsx")

# Scenario 1: Strongly Agree vs. Strongly Disagree
df_filtered_resdim2_scenario1 <- df[df$RESDIM2 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim2_scenario1$Age_Group <- ifelse(df_filtered_resdim2_scenario1$AGE %in% c(3, 4), "35-54", "Other")
table_resdim2_scenario1 <- table(df_filtered_resdim2_scenario1$RESDIM2, df_filtered_resdim2_scenario1$Age_Group)
rownames(table_resdim2_scenario1) <- c("Strongly Agree", "Strongly Disagree")
colnames(table_resdim2_scenario1) <- c("35-54", "Other")
chi_result_resdim2_scenario1 <- chisq.test(table_resdim2_scenario1)
odds_ratio_resdim2_scenario1 <- oddsratio(table_resdim2_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim2_scenario1, caption = "Contingency Table: Age vs. Belief in Solving Antibiotic Resistance (Strongly Disagree vs. Strongly Agree)"))
print(chi_result_resdim2_scenario1)
print(odds_ratio_resdim2_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim2_scenario2 <- df[df$RESDIM2 %in% c(1, 2) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim2_scenario2$Age_Group <- ifelse(df_filtered_resdim2_scenario2$AGE %in% c(3, 4), "35-54", "Other")
table_resdim2_scenario2 <- table(df_filtered_resdim2_scenario2$RESDIM2, df_filtered_resdim2_scenario2$Age_Group)
rownames(table_resdim2_scenario2) <- c("Strongly Disagree", "Neither Agree Nor Disagree")
colnames(table_resdim2_scenario2) <- c("35-54", "Other")
chi_result_resdim2_scenario2 <- chisq.test(table_resdim2_scenario2)
odds_ratio_resdim2_scenario2 <- oddsratio(table_resdim2_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim2_scenario2, caption = "Contingency Table: Age vs. Belief in Solving Antibiotic Resistance (Strongly Disagree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim2_scenario2)
print(odds_ratio_resdim2_scenario2)

# Scenario 3: Strongly Agree + Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim2_scenario3 <- df[df$RESDIM2 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim2_scenario3$Age_Group <- ifelse(df_filtered_resdim2_scenario3$AGE %in% c(3, 4), "35-54", "Other")
df_filtered_resdim2_scenario3$Agree_Neither <- df_filtered_resdim2_scenario3$RESDIM2 %in% c(2, 3)
table_resdim2_scenario3 <- table(df_filtered_resdim2_scenario3$Agree_Neither, df_filtered_resdim2_scenario3$Age_Group)
rownames(table_resdim2_scenario3) <- c("Strongly Disagree", "Strongly Agree + Neither")
colnames(table_resdim2_scenario3) <- c("35-54", "Other")
chi_result_resdim2_scenario3 <- chisq.test(table_resdim2_scenario3)
odds_ratio_resdim2_scenario3 <- oddsratio(table_resdim2_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim2_scenario3, caption = "Contingency Table: Age vs. Belief in Solving Antibiotic Resistance (Strongly Disagree vs. Strongly Agree + Neither Agree Nor Disagree)"))
print(chi_result_resdim2_scenario3)
print(odds_ratio_resdim2_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM3= Everyone needs to use antibiotics responsibly
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_resdim3_scenario1 <- df[df$RESDIM3 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim3_scenario1$Age_Group <- ifelse(df_filtered_resdim3_scenario1$AGE %in% c(3, 4), "35-54", "Other")
table_resdim3_scenario1 <- table(df_filtered_resdim3_scenario1$RESDIM3, df_filtered_resdim3_scenario1$Age_Group)
rownames(table_resdim3_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim3_scenario1) <- c("35-54", "Other")
chi_result_resdim3_scenario1 <- chisq.test(table_resdim3_scenario1)
odds_ratio_resdim3_scenario1 <- oddsratio(table_resdim3_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim3_scenario1, caption = "Contingency Table: Age vs. Everyone needs to use antibiotics responsibly (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_resdim3_scenario1)
print(odds_ratio_resdim3_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim3_scenario2 <- df[df$RESDIM3 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim3_scenario2$Age_Group <- ifelse(df_filtered_resdim3_scenario2$AGE %in% c(3, 4), "35-54", "Other")
table_resdim3_scenario2 <- table(df_filtered_resdim3_scenario2$RESDIM3, df_filtered_resdim3_scenario2$Age_Group)
rownames(table_resdim3_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_resdim3_scenario2) <- c("35-54", "Other")
chi_result_resdim3_scenario2 <- chisq.test(table_resdim3_scenario2)
odds_ratio_resdim3_scenario2 <- oddsratio(table_resdim3_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim3_scenario2, caption = "Contingency Table: Age vs. Everyone needs to use antibiotics responsibly (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim3_scenario2)
print(odds_ratio_resdim3_scenario2)

# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim3_scenario3 <- df[df$RESDIM3 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim3_scenario3$Age_Group <- ifelse(df_filtered_resdim3_scenario3$AGE %in% c(3, 4), "35-54", "Other")
df_filtered_resdim3_scenario3$Disagree_Neither <- df_filtered_resdim3_scenario3$RESDIM3 %in% c(1, 2)
table_resdim3_scenario3 <- table(df_filtered_resdim3_scenario3$Disagree_Neither, df_filtered_resdim3_scenario3$Age_Group)
rownames(table_resdim3_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_resdim3_scenario3) <- c("35-54", "Other")
chi_result_resdim3_scenario3 <- chisq.test(table_resdim3_scenario3)
odds_ratio_resdim3_scenario3 <- oddsratio(table_resdim3_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim3_scenario3, caption = "Contingency Table: Age vs. Everyone needs to use antibiotics responsibly (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_resdim3_scenario3)
print(odds_ratio_resdim3_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM4= People like me can't do much to stop antibiotic resistance
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Agree vs. Strongly Disagree
df_filtered_resdim4_scenario1 <- df[df$RESDIM4 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim4_scenario1$Age_Group <- ifelse(df_filtered_resdim4_scenario1$AGE %in% c(3, 4), "35-54", "Other")
table_resdim4_scenario1 <- table(df_filtered_resdim4_scenario1$RESDIM4, df_filtered_resdim4_scenario1$Age_Group)
rownames(table_resdim4_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim4_scenario1) <- c("35-54", "Other")
chi_result_resdim4_scenario1 <- chisq.test(table_resdim4_scenario1)
odds_ratio_resdim4_scenario1 <- oddsratio(table_resdim4_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim4_scenario1, caption = "Contingency Table: Age vs. Belief in Individual Impact on Antibiotic Resistance (Strongly Disagree vs. Strongly Agree)"))
print(chi_result_resdim4_scenario1)
print(odds_ratio_resdim4_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim4_scenario2 <- df[df$RESDIM4 %in% c(1, 2) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim4_scenario2$Age_Group <- ifelse(df_filtered_resdim4_scenario2$AGE %in% c(3, 4), "35-54", "Other")
table_resdim4_scenario2 <- table(df_filtered_resdim4_scenario2$RESDIM4, df_filtered_resdim4_scenario2$Age_Group)
rownames(table_resdim4_scenario2) <- c("Strongly Disagree", "Neither Agree Nor Disagree")
colnames(table_resdim4_scenario2) <- c("35-54", "Other")
chi_result_resdim4_scenario2 <- chisq.test(table_resdim4_scenario2)
odds_ratio_resdim4_scenario2 <- oddsratio(table_resdim4_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim4_scenario2, caption = "Contingency Table: Age vs. Belief in Individual Impact on Antibiotic Resistance (Strongly Disagree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim4_scenario2)
print(odds_ratio_resdim4_scenario2)

# Scenario 3: Strongly Agree + Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim4_scenario3 <- df[df$RESDIM4 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim4_scenario3$Age_Group <- ifelse(df_filtered_resdim4_scenario3$AGE %in% c(3, 4), "35-54", "Other")
df_filtered_resdim4_scenario3$Agree_Neither <- df_filtered_resdim4_scenario3$RESDIM4 %in% c(2, 3)
table_resdim4_scenario3 <- table(df_filtered_resdim4_scenario3$Agree_Neither, df_filtered_resdim4_scenario3$Age_Group)
rownames(table_resdim4_scenario3) <- c("Strongly Disagree", "Strongly Agree + Neither")
colnames(table_resdim4_scenario3) <- c("35-54", "Other")
chi_result_resdim4_scenario3 <- chisq.test(table_resdim4_scenario3)
odds_ratio_resdim4_scenario3 <- oddsratio(table_resdim4_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim4_scenario3, caption = "Contingency Table: Age vs. Belief in Individual Impact on Antibiotic Resistance (Strongly Disagree vs. Strongly Agree + Neither Agree Nor Disagree)"))
print(chi_result_resdim4_scenario3)
print(odds_ratio_resdim4_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM5= I am worried about the impact that antibiotic resistance will have on my health and that of my family
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_resdim5_scenario1 <- df[df$RESDIM5 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim5_scenario1$Age_Group <- ifelse(df_filtered_resdim5_scenario1$AGE %in% c(3, 4), "35-54", "Other")
table_resdim5_scenario1 <- table(df_filtered_resdim5_scenario1$RESDIM5, df_filtered_resdim5_scenario1$Age_Group)
rownames(table_resdim5_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim5_scenario1) <- c("35-54", "Other")
chi_result_resdim5_scenario1 <- chisq.test(table_resdim5_scenario1)
odds_ratio_resdim5_scenario1 <- oddsratio(table_resdim5_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim5_scenario1, caption = "Contingency Table: Age vs. Impact of AMR on personal health and that of their family (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_resdim5_scenario1)
print(odds_ratio_resdim5_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim5_scenario2 <- df[df$RESDIM5 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim5_scenario2$Age_Group <- ifelse(df_filtered_resdim5_scenario2$AGE %in% c(3, 4), "35-54", "Other")
table_resdim5_scenario2 <- table(df_filtered_resdim5_scenario2$RESDIM5, df_filtered_resdim5_scenario2$Age_Group)
rownames(table_resdim5_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_resdim5_scenario2) <- c("35-54", "Other")
chi_result_resdim5_scenario2 <- chisq.test(table_resdim5_scenario2)
odds_ratio_resdim5_scenario2 <- oddsratio(table_resdim5_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim5_scenario2, caption = "Contingency Table: Age vs. Impact of AMR on personal health and that of their family (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim5_scenario2)
print(odds_ratio_resdim5_scenario2)

# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim5_scenario3 <- df[df$RESDIM5 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim5_scenario3$Age_Group <- ifelse(df_filtered_resdim5_scenario3$AGE %in% c(3, 4), "35-54", "Other")
df_filtered_resdim5_scenario3$Disagree_Neither <- df_filtered_resdim5_scenario3$RESDIM5 %in% c(1, 2)
table_resdim5_scenario3 <- table(df_filtered_resdim5_scenario3$Disagree_Neither, df_filtered_resdim5_scenario3$Age_Group)
rownames(table_resdim5_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_resdim5_scenario3) <- c("35-54", "Other")
chi_result_resdim5_scenario3 <- chisq.test(table_resdim5_scenario3)
odds_ratio_resdim5_scenario3 <- oddsratio(table_resdim5_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim5_scenario3, caption = "Contingency Table: Age vs. Impact of AMR on personal health and that of their family (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_resdim5_scenario3)
print(odds_ratio_resdim5_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM6= I am not at risk of getting an antibiotic-resistant infection, as long as I take my antibiotics correctly
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Agree vs. Strongly Disagree
df_filtered_resdim6_scenario1 <- df[df$RESDIM6 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim6_scenario1$Age_Group <- ifelse(df_filtered_resdim6_scenario1$AGE %in% c(3, 4), "35-54", "Other")
table_resdim6_scenario1 <- table(df_filtered_resdim6_scenario1$RESDIM6, df_filtered_resdim6_scenario1$Age_Group)
rownames(table_resdim6_scenario1) <- c("Strongly Agree", "Strongly Disagree")
colnames(table_resdim6_scenario1) <- c("35-54", "Other")
chi_result_resdim6_scenario1 <- chisq.test(table_resdim6_scenario1)
odds_ratio_resdim6_scenario1 <- oddsratio(table_resdim6_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim6_scenario1, caption = "Contingency Table: Age vs. Perception of Risk of Antibiotic-Resistant Infection (Strongly Disagree vs. Strongly Agree)"))
print(chi_result_resdim6_scenario1)
print(odds_ratio_resdim6_scenario1)
print(table_resdim6_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim6_scenario2 <- df[df$RESDIM6 %in% c(1, 2) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim6_scenario2$Age_Group <- ifelse(df_filtered_resdim6_scenario2$AGE %in% c(3, 4), "35-54", "Other")
table_resdim6_scenario2 <- table(df_filtered_resdim6_scenario2$RESDIM6, df_filtered_resdim6_scenario2$Age_Group)
rownames(table_resdim6_scenario2) <- c("Strongly Disagree", "Neither Agree Nor Disagree")
colnames(table_resdim6_scenario2) <- c("35-54", "Other")
chi_result_resdim6_scenario2 <- chisq.test(table_resdim6_scenario2)
odds_ratio_resdim6_scenario2 <- oddsratio(table_resdim6_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim6_scenario2, caption = "Contingency Table: Age vs. Perception of Risk of Antibiotic-Resistant Infection (Strongly Disagree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim6_scenario2)
print(odds_ratio_resdim6_scenario2)

# Scenario 3: Strongly Agree + Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim6_scenario3 <- df[df$RESDIM6 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim6_scenario3$Age_Group <- ifelse(df_filtered_resdim6_scenario3$AGE %in% c(3, 4), "35-54", "Other")
df_filtered_resdim6_scenario3$Agree_Neither <- df_filtered_resdim6_scenario3$RESDIM6 %in% c(2, 3)
table_resdim6_scenario3 <- table(df_filtered_resdim6_scenario3$Agree_Neither, df_filtered_resdim6_scenario3$Age_Group)
rownames(table_resdim6_scenario3) <- c("Strongly Disagree", "Strongly Agree + Neither")
colnames(table_resdim6_scenario3) <- c("35-54", "Other")
chi_result_resdim6_scenario3 <- chisq.test(table_resdim6_scenario3)
odds_ratio_resdim6_scenario3 <- oddsratio(table_resdim6_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim6_scenario3, caption = "Contingency Table: Age vs. Perception of Risk of Antibiotic-Resistant Infection (Strongly Disagree vs. Strongly Agree + Neither Agree Nor Disagree)"))
print(chi_result_resdim6_scenario3)
print(odds_ratio_resdim6_scenario3)

###############################################  55+ vs. Other ###############################################

###CUSIN1 (I wash my hands before cooking (No= 9.4%))

# Load the Database_simplified dataframe
Database_simplified <- read_excel("C:/Database_simplified.xlsx")

# Filter the DataFrame
df_filtered <- Database_simplified[Database_simplified$CUSIN1 %in% c(0, 1) & Database_simplified$AGE %in% c(1, 2, 3, 4, 5, 6), ]

# Create a new variable for age categorization
df_filtered$Age_Group <- ifelse(df_filtered$AGE %in% c(5, 6), "55+", "Other")

# Create the Contingency Table
table <- table(df_filtered$CUSIN1, df_filtered$Age_Group)

# Add descriptive labels
rownames(table) <- c("CUSIN1 (Yes)", "CUSIN1 (No)")
colnames(table) <- c("55+", "Other")

# Print the contingency table using knitr
kable(table, caption = "Contingency Table: Age Group vs. Hand Washing")

# Chi-Square Test
chi_result <- chisq.test(table)

# Print the results of the Chi-Square Test
print(chi_result)

# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])

# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure

# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

---------------------------------------------------------------------------------------------------
  
  ##CUSIN2 (After handling raw food (meat and vegetables), I wash my hands with soap (No= 15.1%)
  
  df_filtered <- Database_simplified[Database_simplified$CUSIN2 %in% c(0, 1) & Database_simplified$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered$Age_Group <- ifelse(df_filtered$AGE %in% c(5, 6), "55+", "Other")
table <- table(df_filtered$CUSIN2, df_filtered$Age_Group)
rownames(table) <- c("CUSIN2 (Yes)", "CUSIN2 (No)")
colnames(table) <- c("55+", "Other")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: AGE vs. After handling raw food (meat and vegetables), I wash my hands with soap")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN3 (I use the same kitchen utensils for handling raw and ready-to-eat foods (Yes=25.8%))
  
  df_filtered <- Database_simplified[Database_simplified$CUSIN3 %in% c(0, 1) & Database_simplified$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered$Age_Group <- ifelse(df_filtered$AGE %in% c(5, 6), "55+", "Other")
table <- table(df_filtered$CUSIN3, df_filtered$Age_Group)
rownames(table) <- c("CUSIN3 (Yes)", "CUSIN3 (No)")
colnames(table) <- c("55+", "Other")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: AGE vs. I use the same kitchen utensils for handling raw and ready-to-eat foods")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

-------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN4 (I wash kitchen utensils that have been used for raw food before using them to prepare other foods  (No=16.8%))
  
  df_filtered <- Database_simplified[Database_simplified$CUSIN4 %in% c(0, 1) & Database_simplified$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered$Age_Group <- ifelse(df_filtered$AGE %in% c(5, 6), "55+", "Other")
table <- table(df_filtered$CUSIN4, df_filtered$Age_Group)
rownames(table) <- c("CUSIN4 (Yes)", "CUSIN4 (No)")
colnames(table) <- c("55+", "Other")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Age vs. I wash kitchen utensils that have been used for raw food before using them to prepare other foods")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

-------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN5 (I wash fruits and vegetables before eating them (No=20.7%))
  
  df_filtered <- Database_simplified[Database_simplified$CUSIN5 %in% c(0, 1) & Database_simplified$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered$Age_Group <- ifelse(df_filtered$AGE %in% c(5, 6), "55+", "Other")
table <- table(df_filtered$CUSIN5, df_filtered$Age_Group)
rownames(table) <- c("CUSIN5 (Yes)", "CUSIN5 (No)")
colnames(table) <- c("55+", "Other")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Age vs. I wash fruits and vegetables before eating them")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

-------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN6 (I wash my hands before eating (No=21.5))
  
  df_filtered <- Database_simplified[Database_simplified$CUSIN6 %in% c(0, 1) & Database_simplified$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered$Age_Group <- ifelse(df_filtered$AGE %in% c(5, 6), "55+", "Other")
table <- table(df_filtered$CUSIN6, df_filtered$Age_Group)
rownames(table) <- c("CUSIN6 (Yes)", "CUSIN6 (No)")
colnames(table) <- c("55+", "Other")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Age vs. I wash my hands before eating")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

---------------------------------------------------------------------------------------------------------------------
  
  ##PRESCATB1 When you get a prescription for antibiotics, do you follow the recommended 
  ##length of treatment and daily dosage? (No=4.2%) (Sometimes=9.6%) (No+Sometimes=13.8%)
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
df <- Database_simplified
############### 1st scenario= No
df_filtered_prescatb1 <- df[df$PRESCATB1 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_prescatb1$Age_Group <- ifelse(df_filtered_prescatb1$AGE %in% c(5, 6), "55+", "Other")
table_prescatb1 <- table(df_filtered_prescatb1$PRESCATB1, df_filtered_prescatb1$Age_Group)
# Add descriptive labels to the rows and columns
rownames(table_prescatb1) <- c("Yes", "No")
# Perform the Chi-Squared test
chi_result_prescatb1 <- chisq.test(table_prescatb1)
# Calculate the odds ratio and confidence interval
odds_ratio_prescatb1 <- oddsratio(table_prescatb1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_prescatb1, caption = "Contingency Table: Age vs. Following Prescription for Antibiotics"))
# Print the results of the Chi-Squared test
print(chi_result_prescatb1)
# Print the odds ratio and confidence interval
print(odds_ratio_prescatb1)

################## 2nd scenario= Sometimes
df_filtered_prescatb1_sometimes <- df[df$PRESCATB1 %in% c(0, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_prescatb1_sometimes$Age_Group <- ifelse(df_filtered_prescatb1_sometimes$AGE %in% c(5, 6), "55+", "Other")
table_prescatb1_sometimes <- table(df_filtered_prescatb1_sometimes$PRESCATB1, df_filtered_prescatb1_sometimes$Age_Group)
# Add descriptive labels to the rows and columns
rownames(table_prescatb1_sometimes) <- c("Yes", "No")
# Perform the Chi-Squared test
chi_result_prescatb1_sometimes <- chisq.test(table_prescatb1_sometimes)
# Calculate the odds ratio and confidence interval
odds_ratio_prescatb1_sometimes <- oddsratio(table_prescatb1_sometimes, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_prescatb1_sometimes, caption = "Contingency Table: Age vs. Following Prescription for Antibiotics Sometimes"))
# Print the results of the Chi-Squared test
print(chi_result_prescatb1_sometimes)
# Print the odds ratio and confidence interval
print(odds_ratio_prescatb1_sometimes)

################## 3rd scenario= No+Sometimes
# Filter for 'Yes', 'No', and 'Sometimes' responses for PRESCATB1 and genders 'Female' and 'Male'
df_filtered_prescatb1_combined <- df[df$PRESCATB1 %in% c(0, 1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_prescatb1_combined$Age_Group <- ifelse(df_filtered_prescatb1_combined$AGE %in% c(5, 6), "55+", "Other")
df_filtered_prescatb1_combined$No_Sometimes <- df_filtered_prescatb1_combined$PRESCATB1 %in% c(1, 3)
table_prescatb1_combined <- table(df_filtered_prescatb1_combined$No_Sometimes, df_filtered_prescatb1_combined$Age_Group)
# Adjust the table to have 'Yes' and 'No+Sometimes' as row names
rownames(table_prescatb1_combined) <- c("Yes", "No_Sometimes")
# Perform the Chi-Squared test
chi_result_prescatb1_combined <- chisq.test(table_prescatb1_combined)
# Calculate the odds ratio and confidence interval
odds_ratio_prescatb1_combined <- oddsratio(table_prescatb1_combined, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_prescatb1_combined, caption = "Contingency Table: Age vs. Following Prescription for Antibiotics (Yes vs. No+Sometimes)"))
# Print the results of the Chi-Squared test
print(chi_result_prescatb1_combined)
# Print the odds ratio and confidence interval
print(odds_ratio_prescatb1_combined)

---------------------------------------------------------------------------------------------------------------------
  
  ##ARRETATB Do you stop taking antibiotics when symptoms start to disappear?
  ##(Always=7.3%) (Sometimes=20.4%) (Always+Sometimes=27.7%)
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
df <- Database_simplified
############### 1st scenario= Always
df_filtered_arretatb <- df[df$ARRETATB %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_arretatb$Age_Group <- ifelse(df_filtered_arretatb$AGE %in% c(5, 6), "55+", "Other")
table_arretatb <- table(df_filtered_arretatb$ARRETATB, df_filtered_arretatb$Age_Group)
# (Restante do script permanece o mesmo, substituindo 'GENRE' por 'Age_Group')
# Add descriptive labels to the rows and columns
rownames(table_arretatb) <- c("Always", "Never")
# Perform the Chi-Squared test
chi_result_arretatb <- chisq.test(table_arretatb)
# Calculate the odds ratio and confidence interval
odds_ratio_arretatb <- oddsratio(table_arretatb, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_arretatb, caption = "Contingency Table: Age vs. Stopping Antibiotics Always vs. Never"))
# Print the results of the Chi-Squared test
print(chi_result_arretatb)
# Print the odds ratio and confidence interval
print(odds_ratio_arretatb)

################# 2nd Cenario: Sometimes
df_filtered_arretatb_sometimes <- df[df$ARRETATB %in% c(1, 2) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_arretatb_sometimes$Age_Group <- ifelse(df_filtered_arretatb_sometimes$AGE %in% c(5, 6), "55+", "Other")
table_arretatb_sometimes <- table(df_filtered_arretatb_sometimes$ARRETATB == 2, df_filtered_arretatb_sometimes$Age_Group)
# Add descriptive labels to the rows and columns
rownames(table_arretatb_sometimes) <- c("Never", "Sometimes")
# Perform the Chi-Squared test
chi_result_arretatb_sometimes <- chisq.test(table_arretatb_sometimes)
# Calculate the odds ratio and confidence interval
odds_ratio_arretatb_sometimes <- oddsratio(table_arretatb_sometimes, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_arretatb_sometimes, caption = "Contingency Table: Age vs. Stopping Antibiotics Sometimes vs. Never"))
# Print the results of the Chi-Squared test
print(chi_result_arretatb_sometimes)
# Print the odds ratio and confidence interval
print(odds_ratio_arretatb_sometimes)

############### #3rd scenario= Sometimes+Always
df_filtered_arretatb_combined <- df[df$ARRETATB %in% c(0, 1, 2) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_arretatb_combined$Age_Group <- ifelse(df_filtered_arretatb_combined$AGE %in% c(5, 6), "55+", "Other")
df_filtered_arretatb_combined$Sometimes_Always <- df_filtered_arretatb_combined$ARRETATB %in% c(0, 2)
table_arretatb_combined <- table(df_filtered_arretatb_combined$Sometimes_Always, df_filtered_arretatb_combined$Age_Group)
# Add descriptive labels to the rows and columns
rownames(table_arretatb_combined) <- c("Never", "Sometimes_Always")
# Perform the Chi-Squared test
chi_result_arretatb_combined <- chisq.test(table_arretatb_combined)
# Calculate the odds ratio and confidence interval
odds_ratio_arretatb_combined <- oddsratio(table_arretatb_combined, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_arretatb_combined, caption = "Contingency Table: Age vs. Stopping Antibiotics (Sometimes+Always vs. Never)"))
# Print the results of the Chi-Squared test
print(chi_result_arretatb_combined)
# Print the odds ratio and confidence interval
print(odds_ratio_arretatb_combined)

---------------------------------------------------------------------------------------------------------------------
  
  ##ATBORAL1 Have you ever taken an oral antibiotic treatment (by mouth) without a medical prescription? (Yes=12.3%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
df <- Database_simplified  
df_filtered_atboral <- df[df$ATBORAL1 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atboral$Age_Group <- ifelse(df_filtered_atboral$AGE %in% c(5, 6), "55+", "Other")
table_atboral <- table(df_filtered_atboral$ATBORAL1, df_filtered_atboral$Age_Group)
# Add descriptive labels to the rows and columns
rownames(table_atboral) <- c("Yes", "No")
# Perform the Chi-Squared test
chi_result_atboral <- chisq.test(table_atboral)
# Calculate the odds ratio and confidence interval
odds_ratio_atboral <- oddsratio(table_atboral, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atboral, caption = "Contingency Table: Age vs. Taking Oral Antibiotics Without Prescription (Yes vs. No)"))
# Print the results of the Chi-Squared test
print(chi_result_atboral)
# Print the odds ratio and confidence interval
print(odds_ratio_atboral)

--------------------------------------------------------------------------------------------------------
  
  ### ATBANI1 I can exchange resistant bacteria with my pet (False=23.2%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
df <- Database_simplified  
df_filtered_atbani1 <- df[df$ATBANI1 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbani1$Age_Group <- ifelse(df_filtered_atbani1$AGE %in% c(5, 6), "55+", "Other")
table_atbani1 <- table(df_filtered_atbani1$ATBANI1, df_filtered_atbani1$Age_Group)
rownames(table_atbani1) <- c("True", "False")
colnames(table_atbani1) <- c("55+", "Other")
# Perform the Chi-Squared test
chi_result_atbani1 <- chisq.test(table_atbani1)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani1 <- oddsratio(table_atbani1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani1, caption = "Contingency Table: Age vs. Exchanging Resistant Bacteria with Pets (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani1)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani1)

---------------------------------------------------------------------------------------------------------------------
  
  ### ATBANI2=The use of antibiotics in livestock and crops can increase the 
  #presence of resistant bacteria in the environment (False=14.7%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
df <- Database_simplified  
df_filtered_atbani2 <- df[df$ATBANI2 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbani2$Age_Group <- ifelse(df_filtered_atbani2$AGE %in% c(5, 6), "55+", "Other")
table_atbani2 <- table(df_filtered_atbani2$ATBANI2, df_filtered_atbani2$Age_Group)
rownames(table_atbani2) <- c("True", "False")
colnames(table_atbani2) <- c("55+", "Other")
# Perform the Chi-Squared test
chi_result_atbani2 <- chisq.test(table_atbani2)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani2 <- oddsratio(table_atbani2, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani2, caption = "Contingency Table: Age vs. Antibiotics in Livestock and Crops Affecting Environment (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani2)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani2)


--------------------------------------------------------------------------------------------------------------------
  
  ##### ATBANI3	The use of antibiotics in livestock and crops can affect me directly
  ##(I can get resistant bacteria in my body) (False=26.3%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
df <- Database_simplified  
df_filtered_atbani3 <- df[df$ATBANI3 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbani3$Age_Group <- ifelse(df_filtered_atbani3$AGE %in% c(5, 6), "55+", "Other")
table_atbani3 <- table(df_filtered_atbani3$ATBANI3, df_filtered_atbani3$Age_Group)
rownames(table_atbani3) <- c("True", "False")
colnames(table_atbani3) <- c("55+", "Other")
# Perform the Chi-Squared test
chi_result_atbani3 <- chisq.test(table_atbani3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani3 <- oddsratio(table_atbani3, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani3, caption = "Contingency Table: Age vs. Antibiotics in Livestock and Crops Affecting Humans Directly (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani3)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani3)

-------------------------------------------------------------------------------------------------------------------
  ##### ATBANI4	Resistant bacteria are only found in hospitals (True=10.8%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
df <- Database_simplified  
df_filtered_atbani4 <- df[df$ATBANI4 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbani4$Age_Group <- ifelse(df_filtered_atbani4$AGE %in% c(5, 6), "55+", "Other")
table_atbani4 <- table(df_filtered_atbani4$ATBANI4, df_filtered_atbani4$Age_Group)
rownames(table_atbani4) <- c("True", "False")
colnames(table_atbani4) <- c("55+", "Other")
# Perform the Chi-Squared test
chi_result_atbani4 <- chisq.test(table_atbani4)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani4 <- oddsratio(table_atbani4, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani4, caption = "Contingency Table: Age vs. Resistant Bacteria Found Only in Hospitals (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani4)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani4)

----------------------------------------------------------------------------------------------------------------------
  
  #####RESATB1	Antibiotic resistance occurs when your body becomes resistant to antibiotics and they
  ##no longer work as well (True=58.3%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
df <- Database_simplified  
df_filtered_resatb1 <- df[df$RESATB1 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb1$Age_Group <- ifelse(df_filtered_resatb1$AGE %in% c(5, 6), "55+", "Other")
table_resatb1 <- table(df_filtered_resatb1$RESATB1, df_filtered_resatb1$Age_Group)
rownames(table_resatb1) <- c("True", "False")
colnames(table_resatb1) <- c("55+", "Other")
# Perform the Chi-Squared test
chi_result_resatb1 <- chisq.test(table_resatb1)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb1 <- oddsratio(table_resatb1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb1, caption = "Contingency Table: Age vs. Understanding of Antibiotic Resistance (RESATB1: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb1)
print(odds_ratio_resatb1)

-------------------------------------------------------------------------------------------------------------------
  
  #####RESATB2	Many infections are becoming increasingly resistant to antibiotic treatment  (False=12.5%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb2 <- df[df$RESATB2 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb2$Age_Group <- ifelse(df_filtered_resatb2$AGE %in% c(5, 6), "55+", "Other")
table_resatb2 <- table(df_filtered_resatb2$RESATB2, df_filtered_resatb2$Age_Group)
rownames(table_resatb2) <- c("True", "False")
colnames(table_resatb2) <- c("55+", "Other")
# Perform the Chi-Squared test
chi_result_resatb2 <- chisq.test(table_resatb2)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb2 <- oddsratio(table_resatb2, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb2, caption = "Contingency Table: Age vs. Perception of Increasing Infection Resistance (RESATB2: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb2)
print(odds_ratio_resatb2)

---------------------------------------------------------------------------------------------------------------------
  #####RESATB3	If bacteria are resistant to antibiotics, it can be very difficult or impossible to treat the infections they cause (False=16.7%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb3 <- df[df$RESATB3 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb3$Age_Group <- ifelse(df_filtered_resatb3$AGE %in% c(5, 6), "55+", "Other")
table_resatb3 <- table(df_filtered_resatb3$RESATB3, df_filtered_resatb3$Age_Group)
rownames(table_resatb3) <- c("True", "False")
colnames(table_resatb3) <- c("55+", "Other")
# Perform the Chi-Squared test
chi_result_resatb3 <- chisq.test(table_resatb3)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb3 <- oddsratio(table_resatb3, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb3, caption = "Contingency Table: Age vs. Perception of Difficulty Treating Infections (RESATB3: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb3)
print(odds_ratio_resatb3)
----------------------------------------------------------------------------------------------------------------------
  #####RESATB4	Antibiotic resistance is an issue that could affect me or my family (False=11.8%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb4 <- df[df$RESATB4 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb4$Age_Group <- ifelse(df_filtered_resatb4$AGE %in% c(5, 6), "55+", "Other")
table_resatb4 <- table(df_filtered_resatb4$RESATB4, df_filtered_resatb4$Age_Group)
rownames(table_resatb4) <- c("True", "False")
colnames(table_resatb4) <- c("55+", "Other")
# Perform the Chi-Squared test
chi_result_resatb4 <- chisq.test(table_resatb4)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb4 <- oddsratio(table_resatb4, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb4, caption = "Contingency Table: Age vs. Perception of Antibiotic Resistance Affecting One's Family (RESATB4: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb4)
print(odds_ratio_resatb4)

---------------------------------------------------------------------------------------------------------------------
  #####RESATB5	Antibiotic resistance is an issue in other countries but not here (True=9.9%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb5 <- df[df$RESATB5 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb5$Age_Group <- ifelse(df_filtered_resatb5$AGE %in% c(5, 6), "55+", "Other")
table_resatb5 <- table(df_filtered_resatb5$RESATB5, df_filtered_resatb5$Age_Group)
rownames(table_resatb5) <- c("True", "False")
colnames(table_resatb5) <- c("55+", "Other")
# Perform the Chi-Squared test
chi_result_resatb5 <- chisq.test(table_resatb5)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb5 <- oddsratio(table_resatb5, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb5, caption = "Contingency Table: Age vs. Perception of Antibiotic Resistance as an Issue Only in Other Countries (RESATB5: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb5)
print(odds_ratio_resatb5)
---------------------------------------------------------------------------------------------------------------------  
  
  #####RESATB6	Antibiotic resistance is only a problem for people who take antibiotics regularly (True=17.5%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb6 <- df[df$RESATB6 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb6$Age_Group <- ifelse(df_filtered_resatb6$AGE %in% c(5, 6), "55+", "Other")
table_resatb6 <- table(df_filtered_resatb6$RESATB6, df_filtered_resatb6$Age_Group)
rownames(table_resatb6) <- c("True", "False")
colnames(table_resatb6) <- c("55+", "Other")
# Perform the Chi-Squared test
chi_result_resatb6 <- chisq.test(table_resatb6)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb6 <- oddsratio(table_resatb6, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb6, caption = "Contingency Table: Age vs. Perception of Antibiotic Resistance as a Problem Only for Regular Antibiotic Users (RESATB6: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb6)
print(odds_ratio_resatb6)

--------------------------------------------------------------------------------------------------------------------- 
  #####RESATB7	Bacteria that are resistant to antibiotics can be spread from person to person (False=20.2%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb7 <- df[df$RESATB7 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb7$Age_Group <- ifelse(df_filtered_resatb7$AGE %in% c(5, 6), "55+", "Other")
table_resatb7 <- table(df_filtered_resatb7$RESATB7, df_filtered_resatb7$Age_Group)
rownames(table_resatb7) <- c("True", "False")
colnames(table_resatb7) <- c("55+", "Other")
# Perform the Chi-Squared test
chi_result_resatb7 <- chisq.test(table_resatb7)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb7 <- oddsratio(table_resatb7, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb7, caption = "Contingency Table: Age vs. Perception of Bacteria Transmission Person to Person (RESATB7: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb7)
print(odds_ratio_resatb7)

--------------------------------------------------------------------------------------------------------------------
  #####RESATB8	Antibiotic-resistant infections could make medical procedures like surgery, organ transplants,
  ##and cancer treatment much more dangerous (False=12.0%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb8 <- df[df$RESATB8 %in% c(0, 1) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resatb8$Age_Group <- ifelse(df_filtered_resatb8$AGE %in% c(5, 6), "55+", "Other")
table_resatb8 <- table(df_filtered_resatb8$RESATB8, df_filtered_resatb8$Age_Group)
rownames(table_resatb8) <- c("True", "False")
colnames(table_resatb8) <- c("55+", "Other")
# Perform the Chi-Squared test
chi_result_resatb8 <- chisq.test(table_resatb8)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb8 <- oddsratio(table_resatb8, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb8, caption = "Contingency Table: Age vs. Perception of Antibiotic-Resistant Infections and Medical Procedures (RESATB8: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb8)
print(odds_ratio_resatb8)

--------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL1	Farmers should give fewer antibiotics to food-producing animals 
  
  ##################### 1st scenario (Strongly desagree=8.68%) vs. Strongly Agree
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl1_scenario1 <- df[df$ATBRGL1 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl1_scenario1$Age_Group <- ifelse(df_filtered_atbrgl1_scenario1$AGE %in% c(5, 6), "55+", "Other")
table_atbrgl1_scenario1 <- table(df_filtered_atbrgl1_scenario1$ATBRGL1, df_filtered_atbrgl1_scenario1$Age_Group)
rownames(table_atbrgl1_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl1_scenario1) <- c("55+", "Other")
# Perform the Chi-Squared test
chi_result_atbrgl1_scenario1 <- chisq.test(table_atbrgl1_scenario1)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl1_scenario1 <- oddsratio(table_atbrgl1_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl1_scenario1, caption = "Contingency Table: Age vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_atbrgl1_scenario1)
print(odds_ratio_atbrgl1_scenario1)

############################# 2nd scenario Farmers should give fewer antibiotics to
##food-producing animals (Neither agree nor desagree=22.6%) vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl1_scenario2 <- df[df$ATBRGL1 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl1_scenario2$Age_Group <- ifelse(df_filtered_atbrgl1_scenario2$AGE %in% c(5, 6), "55+", "Other")
table_atbrgl1_scenario2 <- table(df_filtered_atbrgl1_scenario2$ATBRGL1, df_filtered_atbrgl1_scenario2$Age_Group)
rownames(table_atbrgl1_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl1_scenario2) <- c("55+", "Other")
# Perform the Chi-Squared test
chi_result_atbrgl1_scenario2 <- chisq.test(table_atbrgl1_scenario2)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl1_scenario2 <- oddsratio(table_atbrgl1_scenario2, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl1_scenario2, caption = "Contingency Table: Age vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Neither Agree Nor Disagree)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_atbrgl1_scenario2)
print(odds_ratio_atbrgl1_scenario2)

############################# 3rd scenario (Strongly desagree + Neither agree nor desagree=31.28%) vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl1_scenario3 <- df[df$ATBRGL1 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl1_scenario3$Age_Group <- ifelse(df_filtered_atbrgl1_scenario3$AGE %in% c(5, 6), "55+", "Other")
df_filtered_atbrgl1_scenario3$Disagree_Neither <- df_filtered_atbrgl1_scenario3$ATBRGL1 %in% c(1, 2)
table_atbrgl1_scenario3 <- table(df_filtered_atbrgl1_scenario3$Disagree_Neither, df_filtered_atbrgl1_scenario3$Age_Group)
rownames(table_atbrgl1_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl1_scenario3) <- c("55+", "Other")
# Perform the Chi-Squared test
chi_result_atbrgl1_scenario3 <- chisq.test(table_atbrgl1_scenario3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl1_scenario3 <- oddsratio(table_atbrgl1_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl1_scenario3, caption = "Contingency Table: Age vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree + Neither)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_atbrgl1_scenario3)
print(odds_ratio_atbrgl1_scenario3)

--------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL2	People should not keep antibiotics and use them later for other illnesses  
  
  ############################# 1st scenario Strongly desagree vs. Strongly Agree
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the database
df <- Database_simplified
## Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_atbrgl2_scenario1 <- df[df$ATBRGL2 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl2_scenario1$Age_Group <- ifelse(df_filtered_atbrgl2_scenario1$AGE %in% c(5, 6), "55+", "Other")
table_atbrgl2_scenario1 <- table(df_filtered_atbrgl2_scenario1$ATBRGL2, df_filtered_atbrgl2_scenario1$Age_Group)
rownames(table_atbrgl2_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl2_scenario1) <- c("55+", "Other")
# Perform Chi-Squared test
chi_result_atbrgl2_scenario1 <- chisq.test(table_atbrgl2_scenario1)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl2_scenario1 <- oddsratio(table_atbrgl2_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl2_scenario1, caption = "Contingency Table: Age vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl2_scenario1)
print(odds_ratio_atbrgl2_scenario1)

############################# 2nd scenario Neither agree nor desagree vs. Strongly Agree
# Filter for 'Strongly Agree' (3) and 'Neither Agree Nor Disagree' (2) responses for ATBRGL2
df_filtered_atbrgl2_scenario2 <- df[df$ATBRGL2 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl2_scenario2$Age_Group <- ifelse(df_filtered_atbrgl2_scenario2$AGE %in% c(5, 6), "55+", "Other")
table_atbrgl2_scenario2 <- table(df_filtered_atbrgl2_scenario2$ATBRGL2, df_filtered_atbrgl2_scenario2$Age_Group)
rownames(table_atbrgl2_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl2_scenario2) <- c("55+", "Other")
# Perform Chi-Squared test
chi_result_atbrgl2_scenario2 <- chisq.test(table_atbrgl2_scenario2)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl2_scenario2 <- oddsratio(table_atbrgl2_scenario2, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl2_scenario2, caption = "Contingency Table: Age vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl2_scenario2)
print(odds_ratio_atbrgl2_scenario2)


############################# 3rd scenario Neither agree nor desagree + Stringly Disagree vs. Strongly Agree
df_filtered_atbrgl2_scenario3 <- df[df$ATBRGL2 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl2_scenario3$Age_Group <- ifelse(df_filtered_atbrgl2_scenario3$AGE %in% c(5, 6), "55+", "Other")
df_filtered_atbrgl2_scenario3$Disagree_Neither <- df_filtered_atbrgl2_scenario3$ATBRGL2 %in% c(1, 2)
table_atbrgl2_scenario3 <- table(df_filtered_atbrgl2_scenario3$Disagree_Neither, df_filtered_atbrgl2_scenario3$Age_Group)
rownames(table_atbrgl2_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl2_scenario3) <- c("55+", "Other")
# Perform the Chi-Squared test
chi_result_atbrgl2_scenario3 <- chisq.test(table_atbrgl2_scenario3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl2_scenario3 <- oddsratio(table_atbrgl2_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl2_scenario3, caption = "Contingency Table: Age vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl2_scenario3)
print(odds_ratio_atbrgl2_scenario3)

--------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL3 Parents should make sure all of their children’s vaccinations are up-to-date 
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)

####1st scenario
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl3_scenario1 <- df[df$ATBRGL3 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl3_scenario1$Age_Group <- ifelse(df_filtered_atbrgl3_scenario1$AGE %in% c(5, 6), "55+", "Other")
table_atbrgl3_scenario1 <- table(df_filtered_atbrgl3_scenario1$ATBRGL3, df_filtered_atbrgl3_scenario1$Age_Group)
rownames(table_atbrgl3_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl3_scenario1) <- c("55+", "Other")
# Perform Chi-Squared test
chi_result_atbrgl3_scenario1 <- chisq.test(table_atbrgl3_scenario1)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl3_scenario1 <- oddsratio(table_atbrgl3_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl3_scenario1, caption = "Contingency Table: Age vs. Opinion on Children's Vaccinations (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl3_scenario1)
print(odds_ratio_atbrgl3_scenario1)

### 2nd Scenario
df_filtered_atbrgl3_scenario2 <- df[df$ATBRGL3 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl3_scenario2$Age_Group <- ifelse(df_filtered_atbrgl3_scenario2$AGE %in% c(5, 6), "55+", "Other")
table_atbrgl3_scenario2 <- table(df_filtered_atbrgl3_scenario2$ATBRGL3, df_filtered_atbrgl3_scenario2$Age_Group)
rownames(table_atbrgl3_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl3_scenario2) <- c("55+", "Other")
# Perform Chi-Squared test
chi_result_atbrgl3_scenario2 <- chisq.test(table_atbrgl3_scenario2)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl3_scenario2 <- oddsratio(table_atbrgl3_scenario2, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl3_scenario2, caption = "Contingency Table: Age vs. Opinion on Children's Vaccinations (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl3_scenario2)
print(odds_ratio_atbrgl3_scenario2)

## 3rd scenario
df_filtered_atbrgl3_scenario3 <- df[df$ATBRGL3 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl3_scenario3$Age_Group <- ifelse(df_filtered_atbrgl3_scenario3$AGE %in% c(5, 6), "55+", "Other")
df_filtered_atbrgl3_scenario3$Disagree_Neither <- df_filtered_atbrgl3_scenario3$ATBRGL3 %in% c(1, 2)
table_atbrgl3_scenario3 <- table(df_filtered_atbrgl3_scenario3$Disagree_Neither, df_filtered_atbrgl3_scenario3$Age_Group)
rownames(table_atbrgl3_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl3_scenario3) <- c("55+", "Other")
# Perform the Chi-Squared test
chi_result_atbrgl3_scenario3 <- chisq.test(table_atbrgl3_scenario3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl3_scenario3 <- oddsratio(table_atbrgl3_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl3_scenario3, caption = "Contingency Table: Age vs. Opinion on Children's Vaccinations (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl3_scenario3)
print(odds_ratio_atbrgl3_scenario3)

---------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL4 People should wash their hands regularly
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

## Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_atbrgl4_scenario1 <- df[df$ATBRGL4 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl4_scenario1$Age_Group <- ifelse(df_filtered_atbrgl4_scenario1$AGE %in% c(5, 6), "55+", "Other")
table_atbrgl4_scenario1 <- table(df_filtered_atbrgl4_scenario1$ATBRGL4, df_filtered_atbrgl4_scenario1$Age_Group)
rownames(table_atbrgl4_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl4_scenario1) <- c("55+", "Other")
chi_result_atbrgl4_scenario1 <- chisq.test(table_atbrgl4_scenario1)
odds_ratio_atbrgl4_scenario1 <- oddsratio(table_atbrgl4_scenario1, conf.level = 0.95)$measure
print(kable(table_atbrgl4_scenario1, caption = "Contingency Table: Age vs. Hand Washing Importance (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl4_scenario1)
print(odds_ratio_atbrgl4_scenario1)

## Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl4_scenario2 <- df[df$ATBRGL4 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl4_scenario2$Age_Group <- ifelse(df_filtered_atbrgl4_scenario2$AGE %in% c(5, 6), "55+", "Other")
table_atbrgl4_scenario2 <- table(df_filtered_atbrgl4_scenario2$ATBRGL4, df_filtered_atbrgl4_scenario2$Age_Group)
rownames(table_atbrgl4_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl4_scenario2) <- c("55+", "Other")
chi_result_atbrgl4_scenario2 <- chisq.test(table_atbrgl4_scenario2)
odds_ratio_atbrgl4_scenario2 <- oddsratio(table_atbrgl4_scenario2, conf.level = 0.95)$measure
print(kable(table_atbrgl4_scenario2, caption = "Contingency Table: Age vs. Hand Washing Importance (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl4_scenario2)
print(odds_ratio_atbrgl4_scenario2)

## Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl4_scenario3 <- df[df$ATBRGL4 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl4_scenario3$Age_Group <- ifelse(df_filtered_atbrgl4_scenario3$AGE %in% c(5, 6), "55+", "Other")
df_filtered_atbrgl4_scenario3$Disagree_Neither <- df_filtered_atbrgl4_scenario3$ATBRGL4 %in% c(1, 2)
table_atbrgl4_scenario3 <- table(df_filtered_atbrgl4_scenario3$Disagree_Neither, df_filtered_atbrgl4_scenario3$Age_Group)
rownames(table_atbrgl4_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl4_scenario3) <- c("18-34", "35+")
chi_result_atbrgl4_scenario3 <- chisq.test(table_atbrgl4_scenario3)
odds_ratio_atbrgl4_scenario3 <- oddsratio(table_atbrgl4_scenario3, conf.level = 0.95)$measure
print(kable(table_atbrgl4_scenario3, caption = "Contingency Table: Age vs. Hand Washing Importance (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl4_scenario3)
print(odds_ratio_atbrgl4_scenario3)

---------------------------------------------------------------------------------------------------------------------
  
  #ATBRGL5 Doctors should only prescribe antibiotics when they are needed 
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)

# Load the Database_simplified dataframe
df <- Database_simplified

## Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_atbrgl5_scenario1 <- df[df$ATBRGL5 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl5_scenario1$Age_Group <- ifelse(df_filtered_atbrgl5_scenario1$AGE %in% c(5, 6), "55+", "Other")
table_atbrgl5_scenario1 <- table(df_filtered_atbrgl5_scenario1$ATBRGL5, df_filtered_atbrgl5_scenario1$Age_Group)
rownames(table_atbrgl5_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl5_scenario1) <- c("55+", "Other")
chi_result_atbrgl5_scenario1 <- chisq.test(table_atbrgl5_scenario1)
odds_ratio_atbrgl5_scenario1 <- oddsratio(table_atbrgl5_scenario1, conf.level = 0.95)$measure
print(kable(table_atbrgl5_scenario1, caption = "Contingency Table: Age vs. Antibiotic Prescription Necessity (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl5_scenario1)
print(odds_ratio_atbrgl5_scenario1)

## Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl5_scenario2 <- df[df$ATBRGL5 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl5_scenario2$Age_Group <- ifelse(df_filtered_atbrgl5_scenario2$AGE %in% c(5, 6), "55+", "Other")
table_atbrgl5_scenario2 <- table(df_filtered_atbrgl5_scenario2$ATBRGL5, df_filtered_atbrgl5_scenario2$Age_Group)
rownames(table_atbrgl5_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl5_scenario2) <- c("55+", "Other")
chi_result_atbrgl5_scenario2 <- chisq.test(table_atbrgl5_scenario2)
odds_ratio_atbrgl5_scenario2 <- oddsratio(table_atbrgl5_scenario2, conf.level = 0.95)$measure
print(kable(table_atbrgl5_scenario2, caption = "Contingency Table: Age vs. Antibiotic Prescription Necessity (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl5_scenario2)
print(odds_ratio_atbrgl5_scenario2)

## Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl5_scenario3 <- df[df$ATBRGL5 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl5_scenario3$Age_Group <- ifelse(df_filtered_atbrgl5_scenario3$AGE %in% c(5, 6), "55+", "Other")
df_filtered_atbrgl5_scenario3$Disagree_Neither <- df_filtered_atbrgl5_scenario3$ATBRGL5 %in% c(1, 2)
table_atbrgl5_scenario3 <- table(df_filtered_atbrgl5_scenario3$Disagree_Neither, df_filtered_atbrgl5_scenario3$Age_Group)
rownames(table_atbrgl5_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl5_scenario3) <- c("55+", "Other")
chi_result_atbrgl5_scenario3 <- chisq.test(table_atbrgl5_scenario3)
odds_ratio_atbrgl5_scenario3 <- oddsratio(table_atbrgl5_scenario3, conf.level = 0.95)$measure
print(kable(table_atbrgl5_scenario3, caption = "Contingency Table: Age vs. Antibiotic Prescription Necessity (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl5_scenario3)
print(odds_ratio_atbrgl5_scenario3)

----------------------------------------------------------------------------------------------------------------------
  
  ##ATBRGL6= People should only use antibiotics when prescribed by a doctor or nurse
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

## Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_atbrgl6_scenario1 <- df[df$ATBRGL6 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl6_scenario1$Age_Group <- ifelse(df_filtered_atbrgl6_scenario1$AGE %in% c(5, 6), "55+", "Other")
table_atbrgl6_scenario1 <- table(df_filtered_atbrgl6_scenario1$ATBRGL6, df_filtered_atbrgl6_scenario1$Age_Group)
rownames(table_atbrgl6_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_atbrgl6_scenario1) <- c("55+", "Other")
chi_result_atbrgl6_scenario1 <- chisq.test(table_atbrgl6_scenario1)
odds_ratio_atbrgl6_scenario1 <- oddsratio(table_atbrgl6_scenario1, conf.level = 0.95)$measure
print(kable(table_atbrgl6_scenario1, caption = "Contingency Table: Age vs. Antibiotic only when prescribed (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl6_scenario1)
print(odds_ratio_atbrgl6_scenario1)

## Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl6_scenario2 <- df[df$ATBRGL6 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl6_scenario2$Age_Group <- ifelse(df_filtered_atbrgl6_scenario2$AGE %in% c(5, 6), "55+", "Other")
table_atbrgl6_scenario2 <- table(df_filtered_atbrgl6_scenario2$ATBRGL6, df_filtered_atbrgl6_scenario2$Age_Group)
rownames(table_atbrgl6_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_atbrgl6_scenario2) <- c("55+", "Other")
chi_result_atbrgl6_scenario2 <- chisq.test(table_atbrgl6_scenario2)
odds_ratio_atbrgl6_scenario2 <- oddsratio(table_atbrgl6_scenario2, conf.level = 0.95)$measure
print(kable(table_atbrgl6_scenario2, caption = "Contingency Table: Age vs. Antibiotic only when prescribed (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl6_scenario2)
print(odds_ratio_atbrgl6_scenario2)

## Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl6_scenario3 <- df[df$ATBRGL6 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl6_scenario3$Age_Group <- ifelse(df_filtered_atbrgl6_scenario3$AGE %in% c(5, 6), "55+", "Other")
df_filtered_atbrgl6_scenario3$Disagree_Neither <- df_filtered_atbrgl6_scenario3$ATBRGL6 %in% c(1, 2)
table_atbrgl6_scenario3 <- table(df_filtered_atbrgl6_scenario3$Disagree_Neither, df_filtered_atbrgl6_scenario3$Age_Group)
rownames(table_atbrgl6_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_atbrgl6_scenario3) <- c("55+", "Other")
chi_result_atbrgl6_scenario3 <- chisq.test(table_atbrgl6_scenario3)
odds_ratio_atbrgl6_scenario3 <- oddsratio(table_atbrgl6_scenario3, conf.level = 0.95)$measure
print(kable(table_atbrgl6_scenario3, caption = "Contingency Table: Age vs. Antibiotic only when prescribed (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl6_scenario3)
print(odds_ratio_atbrgl6_scenario3)

----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM1= Antibiotic resistance is one of the biggest problems the world faces
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_resdim1_scenario1 <- df[df$RESDIM1 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim1_scenario1$Age_Group <- ifelse(df_filtered_resdim1_scenario1$AGE %in% c(5, 6), "55+", "Other")
table_resdim1_scenario1 <- table(df_filtered_resdim1_scenario1$RESDIM1, df_filtered_resdim1_scenario1$Age_Group)
rownames(table_resdim1_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim1_scenario1) <- c("55+", "Other")
chi_result_resdim1_scenario1 <- chisq.test(table_resdim1_scenario1)
odds_ratio_resdim1_scenario1 <- oddsratio(table_resdim1_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim1_scenario1, caption = "Contingency Table: Age vs. Perception of Antibiotic Resistance as a Global Problem (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_resdim1_scenario1)
print(odds_ratio_resdim1_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim1_scenario2 <- df[df$RESDIM1 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim1_scenario2$Age_Group <- ifelse(df_filtered_resdim1_scenario2$AGE %in% c(5, 6), "55+", "Other")
table_resdim1_scenario2 <- table(df_filtered_resdim1_scenario2$RESDIM1, df_filtered_resdim1_scenario2$Age_Group)
rownames(table_resdim1_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_resdim1_scenario2) <- c("55+", "Other")
chi_result_resdim1_scenario2 <- chisq.test(table_resdim1_scenario2)
odds_ratio_resdim1_scenario2 <- oddsratio(table_resdim1_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim1_scenario2, caption = "Contingency Table: Age vs. Perception of Antibiotic Resistance as a Global Problem (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim1_scenario2)
print(odds_ratio_resdim1_scenario2)

# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim1_scenario3 <- df[df$RESDIM1 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim1_scenario3$Age_Group <- ifelse(df_filtered_resdim1_scenario3$AGE %in% c(5, 6), "55+", "Other")
df_filtered_resdim1_scenario3$Disagree_Neither <- df_filtered_resdim1_scenario3$RESDIM1 %in% c(1, 2)
table_resdim1_scenario3 <- table(df_filtered_resdim1_scenario3$Disagree_Neither, df_filtered_resdim1_scenario3$Age_Group)
rownames(table_resdim1_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_resdim1_scenario3) <- c("55+", "Other")
chi_result_resdim1_scenario3 <- chisq.test(table_resdim1_scenario3)
odds_ratio_resdim1_scenario3 <- oddsratio(table_resdim1_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim1_scenario3, caption = "Contingency Table: Age vs. Perception of Antibiotic Resistance as a Global Problem (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_resdim1_scenario3)
print(odds_ratio_resdim1_scenario3)

----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM2= Medical experts will solve the problem of antibiotic resistance before it becomes too serious 
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Load the Database_simplified dataframe
df <- read_excel("C:/Database_simplified.xlsx")

# Scenario 1: Strongly Agree vs. Strongly Disagree
df_filtered_resdim2_scenario1 <- df[df$RESDIM2 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim2_scenario1$Age_Group <- ifelse(df_filtered_resdim2_scenario1$AGE %in% c(5, 6), "55+", "Other")
table_resdim2_scenario1 <- table(df_filtered_resdim2_scenario1$RESDIM2, df_filtered_resdim2_scenario1$Age_Group)
rownames(table_resdim2_scenario1) <- c("Strongly Agree", "Strongly Disagree")
colnames(table_resdim2_scenario1) <- c("55+", "Other")
chi_result_resdim2_scenario1 <- chisq.test(table_resdim2_scenario1)
odds_ratio_resdim2_scenario1 <- oddsratio(table_resdim2_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim2_scenario1, caption = "Contingency Table: Age vs. Belief in Solving Antibiotic Resistance (Strongly Disagree vs. Strongly Agree)"))
print(chi_result_resdim2_scenario1)
print(odds_ratio_resdim2_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim2_scenario2 <- df[df$RESDIM2 %in% c(1, 2) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim2_scenario2$Age_Group <- ifelse(df_filtered_resdim2_scenario2$AGE %in% c(5, 6), "55+", "Other")
table_resdim2_scenario2 <- table(df_filtered_resdim2_scenario2$RESDIM2, df_filtered_resdim2_scenario2$Age_Group)
rownames(table_resdim2_scenario2) <- c("Strongly Disagree", "Neither Agree Nor Disagree")
colnames(table_resdim2_scenario2) <- c("55+", "Other")
chi_result_resdim2_scenario2 <- chisq.test(table_resdim2_scenario2)
odds_ratio_resdim2_scenario2 <- oddsratio(table_resdim2_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim2_scenario2, caption = "Contingency Table: Age vs. Belief in Solving Antibiotic Resistance (Strongly Disagree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim2_scenario2)
print(odds_ratio_resdim2_scenario2)

# Scenario 3: Strongly Agree + Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim2_scenario3 <- df[df$RESDIM2 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim2_scenario3$Age_Group <- ifelse(df_filtered_resdim2_scenario3$AGE %in% c(5, 6), "55+", "Other")
df_filtered_resdim2_scenario3$Agree_Neither <- df_filtered_resdim2_scenario3$RESDIM2 %in% c(2, 3)
table_resdim2_scenario3 <- table(df_filtered_resdim2_scenario3$Agree_Neither, df_filtered_resdim2_scenario3$Age_Group)
rownames(table_resdim2_scenario3) <- c("Strongly Disagree", "Strongly Agree + Neither")
colnames(table_resdim2_scenario3) <- c("55+", "Other")
chi_result_resdim2_scenario3 <- chisq.test(table_resdim2_scenario3)
odds_ratio_resdim2_scenario3 <- oddsratio(table_resdim2_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim2_scenario3, caption = "Contingency Table: Age vs. Belief in Solving Antibiotic Resistance (Strongly Disagree vs. Strongly Agree + Neither Agree Nor Disagree)"))
print(chi_result_resdim2_scenario3)
print(odds_ratio_resdim2_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM3= Everyone needs to use antibiotics responsibly
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_resdim3_scenario1 <- df[df$RESDIM3 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim3_scenario1$Age_Group <- ifelse(df_filtered_resdim3_scenario1$AGE %in% c(5, 6), "55+", "Other")
table_resdim3_scenario1 <- table(df_filtered_resdim3_scenario1$RESDIM3, df_filtered_resdim3_scenario1$Age_Group)
rownames(table_resdim3_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim3_scenario1) <- c("55+", "Other")
chi_result_resdim3_scenario1 <- chisq.test(table_resdim3_scenario1)
odds_ratio_resdim3_scenario1 <- oddsratio(table_resdim3_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim3_scenario1, caption = "Contingency Table: Age vs. Everyone needs to use antibiotics responsibly (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_resdim3_scenario1)
print(odds_ratio_resdim3_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim3_scenario2 <- df[df$RESDIM3 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim3_scenario2$Age_Group <- ifelse(df_filtered_resdim3_scenario2$AGE %in% c(5, 6), "55+", "Other")
table_resdim3_scenario2 <- table(df_filtered_resdim3_scenario2$RESDIM3, df_filtered_resdim3_scenario2$Age_Group)
rownames(table_resdim3_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_resdim3_scenario2) <- c("55+", "Other")
chi_result_resdim3_scenario2 <- chisq.test(table_resdim3_scenario2)
odds_ratio_resdim3_scenario2 <- oddsratio(table_resdim3_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim3_scenario2, caption = "Contingency Table: Age vs. Everyone needs to use antibiotics responsibly (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim3_scenario2)
print(odds_ratio_resdim3_scenario2)

# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim3_scenario3 <- df[df$RESDIM3 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim3_scenario3$Age_Group <- ifelse(df_filtered_resdim3_scenario3$AGE %in% c(5, 6), "55+", "Other")
df_filtered_resdim3_scenario3$Disagree_Neither <- df_filtered_resdim3_scenario3$RESDIM3 %in% c(1, 2)
table_resdim3_scenario3 <- table(df_filtered_resdim3_scenario3$Disagree_Neither, df_filtered_resdim3_scenario3$Age_Group)
rownames(table_resdim3_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_resdim3_scenario3) <- c("55+", "Other")
chi_result_resdim3_scenario3 <- chisq.test(table_resdim3_scenario3)
odds_ratio_resdim3_scenario3 <- oddsratio(table_resdim3_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim3_scenario3, caption = "Contingency Table: Age vs. Everyone needs to use antibiotics responsibly (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_resdim3_scenario3)
print(odds_ratio_resdim3_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM4= People like me can't do much to stop antibiotic resistance
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Agree vs. Strongly Disagree
df_filtered_resdim4_scenario1 <- df[df$RESDIM4 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim4_scenario1$Age_Group <- ifelse(df_filtered_resdim4_scenario1$AGE %in% c(5, 6), "55+", "Other")
table_resdim4_scenario1 <- table(df_filtered_resdim4_scenario1$RESDIM4, df_filtered_resdim4_scenario1$Age_Group)
rownames(table_resdim4_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim4_scenario1) <- c("55+", "Other")
chi_result_resdim4_scenario1 <- chisq.test(table_resdim4_scenario1)
odds_ratio_resdim4_scenario1 <- oddsratio(table_resdim4_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim4_scenario1, caption = "Contingency Table: Age vs. Belief in Individual Impact on Antibiotic Resistance (Strongly Disagree vs. Strongly Agree)"))
print(chi_result_resdim4_scenario1)
print(odds_ratio_resdim4_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim4_scenario2 <- df[df$RESDIM4 %in% c(1, 2) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim4_scenario2$Age_Group <- ifelse(df_filtered_resdim4_scenario2$AGE %in% c(5, 6), "55+", "Other")
table_resdim4_scenario2 <- table(df_filtered_resdim4_scenario2$RESDIM4, df_filtered_resdim4_scenario2$Age_Group)
rownames(table_resdim4_scenario2) <- c("Strongly Disagree", "Neither Agree Nor Disagree")
colnames(table_resdim4_scenario2) <- c("55+", "Other")
chi_result_resdim4_scenario2 <- chisq.test(table_resdim4_scenario2)
odds_ratio_resdim4_scenario2 <- oddsratio(table_resdim4_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim4_scenario2, caption = "Contingency Table: Age vs. Belief in Individual Impact on Antibiotic Resistance (Strongly Disagree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim4_scenario2)
print(odds_ratio_resdim4_scenario2)

# Scenario 3: Strongly Agree + Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim4_scenario3 <- df[df$RESDIM4 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim4_scenario3$Age_Group <- ifelse(df_filtered_resdim4_scenario3$AGE %in% c(5, 6), "55+", "Other")
df_filtered_resdim4_scenario3$Agree_Neither <- df_filtered_resdim4_scenario3$RESDIM4 %in% c(2, 3)
table_resdim4_scenario3 <- table(df_filtered_resdim4_scenario3$Agree_Neither, df_filtered_resdim4_scenario3$Age_Group)
rownames(table_resdim4_scenario3) <- c("Strongly Disagree", "Strongly Agree + Neither")
colnames(table_resdim4_scenario3) <- c("55+", "Other")
chi_result_resdim4_scenario3 <- chisq.test(table_resdim4_scenario3)
odds_ratio_resdim4_scenario3 <- oddsratio(table_resdim4_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim4_scenario3, caption = "Contingency Table: Age vs. Belief in Individual Impact on Antibiotic Resistance (Strongly Disagree vs. Strongly Agree + Neither Agree Nor Disagree)"))
print(chi_result_resdim4_scenario3)
print(odds_ratio_resdim4_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM5= I am worried about the impact that antibiotic resistance will have on my health and that of my family
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_resdim5_scenario1 <- df[df$RESDIM5 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim5_scenario1$Age_Group <- ifelse(df_filtered_resdim5_scenario1$AGE %in% c(5, 6), "55+", "Other")
table_resdim5_scenario1 <- table(df_filtered_resdim5_scenario1$RESDIM5, df_filtered_resdim5_scenario1$Age_Group)
rownames(table_resdim5_scenario1) <- c("Strongly Disagree", "Strongly Agree")
colnames(table_resdim5_scenario1) <- c("55+", "Other")
chi_result_resdim5_scenario1 <- chisq.test(table_resdim5_scenario1)
odds_ratio_resdim5_scenario1 <- oddsratio(table_resdim5_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim5_scenario1, caption = "Contingency Table: Age vs. Impact of AMR on personal health and that of their family (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_resdim5_scenario1)
print(odds_ratio_resdim5_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim5_scenario2 <- df[df$RESDIM5 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim5_scenario2$Age_Group <- ifelse(df_filtered_resdim5_scenario2$AGE %in% c(5, 6), "55+", "Other")
table_resdim5_scenario2 <- table(df_filtered_resdim5_scenario2$RESDIM5, df_filtered_resdim5_scenario2$Age_Group)
rownames(table_resdim5_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
colnames(table_resdim5_scenario2) <- c("55+", "Other")
chi_result_resdim5_scenario2 <- chisq.test(table_resdim5_scenario2)
odds_ratio_resdim5_scenario2 <- oddsratio(table_resdim5_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim5_scenario2, caption = "Contingency Table: Age vs. Impact of AMR on personal health and that of their family (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim5_scenario2)
print(odds_ratio_resdim5_scenario2)

# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim5_scenario3 <- df[df$RESDIM5 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim5_scenario3$Age_Group <- ifelse(df_filtered_resdim5_scenario3$AGE %in% c(5, 6), "55+", "Other")
df_filtered_resdim5_scenario3$Disagree_Neither <- df_filtered_resdim5_scenario3$RESDIM5 %in% c(1, 2)
table_resdim5_scenario3 <- table(df_filtered_resdim5_scenario3$Disagree_Neither, df_filtered_resdim5_scenario3$Age_Group)
rownames(table_resdim5_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
colnames(table_resdim5_scenario3) <- c("55+", "Other")
chi_result_resdim5_scenario3 <- chisq.test(table_resdim5_scenario3)
odds_ratio_resdim5_scenario3 <- oddsratio(table_resdim5_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim5_scenario3, caption = "Contingency Table: Age vs. Impact of AMR on personal health and that of their family (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_resdim5_scenario3)
print(odds_ratio_resdim5_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM6= I am not at risk of getting an antibiotic-resistant infection, as long as I take my antibiotics correctly
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Agree vs. Strongly Disagree
df_filtered_resdim6_scenario1 <- df[df$RESDIM6 %in% c(1, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim6_scenario1$Age_Group <- ifelse(df_filtered_resdim6_scenario1$AGE %in% c(5, 6), "55+", "Other")
table_resdim6_scenario1 <- table(df_filtered_resdim6_scenario1$RESDIM6, df_filtered_resdim6_scenario1$Age_Group)
rownames(table_resdim6_scenario1) <- c("Strongly Agree", "Strongly Disagree")
colnames(table_resdim6_scenario1) <- c("55+", "Other")
chi_result_resdim6_scenario1 <- chisq.test(table_resdim6_scenario1)
odds_ratio_resdim6_scenario1 <- oddsratio(table_resdim6_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim6_scenario1, caption = "Contingency Table: Age vs. Perception of Risk of Antibiotic-Resistant Infection (Strongly Disagree vs. Strongly Agree)"))
print(chi_result_resdim6_scenario1)
print(odds_ratio_resdim6_scenario1)
print(table_resdim6_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim6_scenario2 <- df[df$RESDIM6 %in% c(1, 2) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim6_scenario2$Age_Group <- ifelse(df_filtered_resdim6_scenario2$AGE %in% c(5, 6), "55+", "Other")
table_resdim6_scenario2 <- table(df_filtered_resdim6_scenario2$RESDIM6, df_filtered_resdim6_scenario2$Age_Group)
rownames(table_resdim6_scenario2) <- c("Strongly Disagree", "Neither Agree Nor Disagree")
colnames(table_resdim6_scenario2) <- c("55+", "Other")
chi_result_resdim6_scenario2 <- chisq.test(table_resdim6_scenario2)
odds_ratio_resdim6_scenario2 <- oddsratio(table_resdim6_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim6_scenario2, caption = "Contingency Table: Age vs. Perception of Risk of Antibiotic-Resistant Infection (Strongly Disagree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim6_scenario2)
print(odds_ratio_resdim6_scenario2)

# Scenario 3: Strongly Agree + Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim6_scenario3 <- df[df$RESDIM6 %in% c(1, 2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_resdim6_scenario3$Age_Group <- ifelse(df_filtered_resdim6_scenario3$AGE %in% c(5, 6), "55+", "Other")
df_filtered_resdim6_scenario3$Agree_Neither <- df_filtered_resdim6_scenario3$RESDIM6 %in% c(2, 3)
table_resdim6_scenario3 <- table(df_filtered_resdim6_scenario3$Agree_Neither, df_filtered_resdim6_scenario3$Age_Group)
rownames(table_resdim6_scenario3) <- c("Strongly Disagree", "Strongly Agree + Neither")
colnames(table_resdim6_scenario3) <- c("55+", "Other")
chi_result_resdim6_scenario3 <- chisq.test(table_resdim6_scenario3)
odds_ratio_resdim6_scenario3 <- oddsratio(table_resdim6_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim6_scenario3, caption = "Contingency Table: Age vs. Perception of Risk of Antibiotic-Resistant Infection (Strongly Disagree vs. Strongly Agree + Neither Agree Nor Disagree)"))
print(chi_result_resdim6_scenario3)
print(odds_ratio_resdim6_scenario3)


############################################### Comparasions by Level of education (Higher education vs Other) #######################################


###CUSIN1 (I wash my hands before cooking (No= 9.4%))

# Load the Database_simplified dataframe
Database_simplified <- read_excel("C:/Database_simplified.xlsx")

# Filter DataFrame to include only the relevant education levels and the CUSIN1 variable
df_filtered <- Database_simplified[Database_simplified$CUSIN1 %in% c(0, 1) & 
                                     Database_simplified$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]

# Create a binary variable for NIVSCOL
df_filtered$Education_Level <- ifelse(df_filtered$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")

# Create the Contingency Table
table <- table(df_filtered$CUSIN1, df_filtered$Education_Level)

# Rename rows and columns of the table
rownames(table) <- c("CUSIN1 (Yes)", "CUSIN1 (No)")
# Print the contingency table using knitr
kable(table, caption = "Contingency Table: Education vs. Hand Washing")

# Chi-Square Test
chi_result <- chisq.test(table)

# Print the results of the Chi-Square Test
print(chi_result)

# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])

# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure

# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

---------------------------------------------------------------------------------------------------
  
  ##CUSIN2 (After handling raw food (meat and vegetables), I wash my hands with soap (No= 15.1%)
  
  # Filter DataFrame to include only the relevant education levels and the CUSIN2 variable
  df_filtered <- Database_simplified[Database_simplified$CUSIN2 %in% c(0, 1) & 
                                       Database_simplified$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
# Create a binary variable for NIVSCOL
df_filtered$Education_Level <- ifelse(df_filtered$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
# Create the Contingency Table
table <- table(df_filtered$CUSIN2, df_filtered$Education_Level)
# Rename rows and columns of the table
rownames(table) <- c("CUSIN2 (Yes)", "CUSIN2 (No)")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Education vs. After handling raw food (meat and vegetables), I wash my hands with soap")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN3 (I use the same kitchen utensils for handling raw and ready-to-eat foods (Yes=25.8%))
  
  # Filter DataFrame to include only the relevant education levels and the CUSIN3 variable
  df_filtered <- Database_simplified[Database_simplified$CUSIN3 %in% c(0, 1) & 
                                       Database_simplified$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
# Create a binary variable for NIVSCOL
df_filtered$Education_Level <- ifelse(df_filtered$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
# Create the Contingency Table
table <- table(df_filtered$CUSIN3, df_filtered$Education_Level)
# Rename rows and columns of the table
rownames(table) <- c("CUSIN3 (Yes)", "CUSIN3 (No)")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Education vs. I use the same kitchen utensils for handling raw and ready-to-eat foods")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

-------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN4 (I wash kitchen utensils that have been used for raw food before using them to prepare other foods  (No=16.8%))
  
  # Filter DataFrame to include only the relevant education levels and the CUSIN4 variable
  df_filtered <- Database_simplified[Database_simplified$CUSIN4 %in% c(0, 1) & 
                                       Database_simplified$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
# Create a binary variable for NIVSCOL
df_filtered$Education_Level <- ifelse(df_filtered$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
# Create the Contingency Table
table <- table(df_filtered$CUSIN4, df_filtered$Education_Level)
# Rename rows and columns of the table
rownames(table) <- c("CUSIN4 (Yes)", "CUSIN4 (No)")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Education Level vs. Washing Kitchen Utensils Used for Raw Food Before Using Them for Other Foods")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

-------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN5 (I wash fruits and vegetables before eating them (No=20.7%))
  
  # Filter DataFrame to include only the relevant education levels and the CUSIN5 variable
  df_filtered <- Database_simplified[Database_simplified$CUSIN5 %in% c(0, 1) & 
                                       Database_simplified$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
# Create a binary variable for NIVSCOL
df_filtered$Education_Level <- ifelse(df_filtered$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
# Create the Contingency Table
table <- table(df_filtered$CUSIN5, df_filtered$Education_Level)
# Rename rows and columns of the table
rownames(table) <- c("CUSIN5 (Yes)", "CUSIN5 (No)")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Education Level vs. Washing Fruits and Vegetables Before Eating Them")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

-------------------------------------------------------------------------------------------------------------------
  ##CUSIN6 (I wash my hands before eating (No=21.5))
  
  # Filter DataFrame to include only the relevant education levels and the CUSIN6 variable
  df_filtered <- Database_simplified[Database_simplified$CUSIN6 %in% c(0, 1) & 
                                       Database_simplified$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
# Create a binary variable for NIVSCOL
df_filtered$Education_Level <- ifelse(df_filtered$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
# Create the Contingency Table
table <- table(df_filtered$CUSIN6, df_filtered$Education_Level)
# Rename rows and columns of the table
rownames(table) <- c("CUSIN6 (Yes)", "CUSIN6 (No)")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Education Level vs. Washing Hands Before Eating")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

---------------------------------------------------------------------------------------------------------------------
  
  ##PRESCATB1 When you get a prescription for antibiotics, do you follow the recommended 
  ##length of treatment and daily dosage? (No=4.2%) (Sometimes=9.6%) (No+Sometimes=13.8%)
  
  # Read the database
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
df <- Database_simplified

############### 1st scenario= No
df_filtered_prescatb1 <- df[df$PRESCATB1 %in% c(0, 1) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_prescatb1$Education_Level <- ifelse(df_filtered_prescatb1$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_prescatb1 <- table(df_filtered_prescatb1$PRESCATB1, df_filtered_prescatb1$Education_Level)
# Add descriptive labels to the rows and columns
rownames(table_prescatb1) <- c("Yes", "No")
# Perform the Chi-Squared test
chi_result_prescatb1 <- chisq.test(table_prescatb1)
# Calculate the odds ratio and confidence interval
odds_ratio_prescatb1 <- oddsratio(table_prescatb1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_prescatb1, caption = "Contingency Table: Age vs. Following Prescription for Antibiotics"))
# Print the results of the Chi-Squared test
print(chi_result_prescatb1)
# Print the odds ratio and confidence interval
print(odds_ratio_prescatb1)

################## 2nd scenario= Sometimes
df_filtered_prescatb1_sometimes <- df[df$PRESCATB1 %in% c(0, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_prescatb1_sometimes$Education_Level <- ifelse(df_filtered_prescatb1_sometimes$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_prescatb1_sometimes <- table(df_filtered_prescatb1_sometimes$PRESCATB1, df_filtered_prescatb1_sometimes$Education_Level)
# Add descriptive labels to the rows and columns
rownames(table_prescatb1_sometimes) <- c("Yes", "Sometimes")
# Perform the Chi-Squared test
chi_result_prescatb1_sometimes <- chisq.test(table_prescatb1_sometimes)
# Calculate the odds ratio and confidence interval
odds_ratio_prescatb1_sometimes <- oddsratio(table_prescatb1_sometimes, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_prescatb1_sometimes, caption = "Contingency Table: Age vs. Following Prescription for Antibiotics Sometimes"))
# Print the results of the Chi-Squared test
print(chi_result_prescatb1_sometimes)
# Print the odds ratio and confidence interval
print(odds_ratio_prescatb1_sometimes)

################## 3rd scenario= No+Sometimes
df_filtered_prescatb1_combined <- df[df$PRESCATB1 %in% c(0, 1, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_prescatb1_combined$Education_Level <- ifelse(df_filtered_prescatb1_combined$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
df_filtered_prescatb1_combined$No_Sometimes <- df_filtered_prescatb1_combined$PRESCATB1 %in% c(1, 3)
table_prescatb1_combined <- table(df_filtered_prescatb1_combined$No_Sometimes, df_filtered_prescatb1_combined$Education_Level)
# Adjust the table to have 'Yes' and 'No+Sometimes' as row names
rownames(table_prescatb1_combined) <- c("Yes", "No_Sometimes")
# Perform the Chi-Squared test
chi_result_prescatb1_combined <- chisq.test(table_prescatb1_combined)
# Calculate the odds ratio and confidence interval
odds_ratio_prescatb1_combined <- oddsratio(table_prescatb1_combined, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_prescatb1_combined, caption = "Contingency Table: Age vs. Following Prescription for Antibiotics (Yes vs. No+Sometimes)"))
# Print the results of the Chi-Squared test
print(chi_result_prescatb1_combined)
# Print the odds ratio and confidence interval
print(odds_ratio_prescatb1_combined)

---------------------------------------------------------------------------------------------------------------------
  
  ##ARRETATB Do you stop taking antibiotics when symptoms start to disappear?
  ##(Always=7.3%) (Sometimes=20.4%) (Always+Sometimes=27.7%)
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
df <- Database_simplified
############### 1st scenario= Always
df_filtered_arretatb <- df[df$ARRETATB %in% c(0, 1) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_arretatb$Education_Level <- ifelse(df_filtered_arretatb$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_arretatb <- table(df_filtered_arretatb$ARRETATB, df_filtered_arretatb$Education_Level)
# Add descriptive labels to the rows and columns
rownames(table_arretatb) <- c("Always", "Never")
# Perform the Chi-Squared test
chi_result_arretatb <- chisq.test(table_arretatb)
# Calculate the odds ratio and confidence interval
odds_ratio_arretatb <- oddsratio(table_arretatb, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_arretatb, caption = "Contingency Table: Age vs. Stopping Antibiotics Always vs. Never"))
# Print the results of the Chi-Squared test
print(chi_result_arretatb)
# Print the odds ratio and confidence interval
print(odds_ratio_arretatb)

################# 2nd scenario: Sometimes
df_filtered_arretatb_sometimes <- df[df$ARRETATB %in% c(1, 2) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_arretatb_sometimes$Education_Level <- ifelse(df_filtered_arretatb_sometimes$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_arretatb_sometimes <- table(df_filtered_arretatb_sometimes$ARRETATB == 2, df_filtered_arretatb_sometimes$Education_Level)
# Add descriptive labels to the rows and columns
rownames(table_arretatb_sometimes) <- c("Never", "Sometimes")
# Perform the Chi-Squared test
chi_result_arretatb_sometimes <- chisq.test(table_arretatb_sometimes)
# Calculate the odds ratio and confidence interval
odds_ratio_arretatb_sometimes <- oddsratio(table_arretatb_sometimes, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_arretatb_sometimes, caption = "Contingency Table: Age vs. Stopping Antibiotics Sometimes vs. Never"))
# Print the results of the Chi-Squared test
print(chi_result_arretatb_sometimes)
# Print the odds ratio and confidence interval
print(odds_ratio_arretatb_sometimes)

############### #3rd scenario= Sometimes+Always
df_filtered_arretatb_combined <- df[df$ARRETATB %in% c(0, 1, 2) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_arretatb_combined$Education_Level <- ifelse(df_filtered_arretatb_combined$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
df_filtered_arretatb_combined$Sometimes_Always <- df_filtered_arretatb_combined$ARRETATB %in% c(0, 2)
table_arretatb_combined <- table(df_filtered_arretatb_combined$Sometimes_Always, df_filtered_arretatb_combined$Education_Level)
# Add descriptive labels to the rows and columns
rownames(table_arretatb_combined) <- c("Never", "Sometimes_Always")
# Perform the Chi-Squared test
chi_result_arretatb_combined <- chisq.test(table_arretatb_combined)
# Calculate the odds ratio and confidence interval
odds_ratio_arretatb_combined <- oddsratio(table_arretatb_combined, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_arretatb_combined, caption = "Contingency Table: Age vs. Stopping Antibiotics (Sometimes+Always vs. Never)"))
# Print the results of the Chi-Squared test
print(chi_result_arretatb_combined)
# Print the odds ratio and confidence interval
print(odds_ratio_arretatb_combined)

---------------------------------------------------------------------------------------------------------------------
  
  ##ATBORAL1 Have you ever taken an oral antibiotic treatment (by mouth) without a medical prescription? (Yes=12.3%)
  # Filter DataFrame for the relevant education levels and ATBORAL1 variable
  df_filtered_atboral <- df[df$ATBORAL1 %in% c(0, 1) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atboral$Education_Level <- ifelse(df_filtered_atboral$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_atboral <- table(df_filtered_atboral$ATBORAL1, df_filtered_atboral$Education_Level)
# Add descriptive labels to the rows and columns
rownames(table_atboral) <- c("Yes", "No")
# Perform the Chi-Squared test
chi_result_atboral <- chisq.test(table_atboral)
# Calculate the odds ratio and confidence interval
odds_ratio_atboral <- oddsratio(table_atboral, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atboral, caption = "Contingency Table: Education Level vs. Taking Oral Antibiotics Without Prescription (Yes vs. No)"))
# Print the results of the Chi-Squared test
print(chi_result_atboral)
# Print the odds ratio and confidence interval
print(odds_ratio_atboral)

--------------------------------------------------------------------------------------------------------
  
  ### ATBANI1 I can exchange resistant bacteria with my pet (False=23.2%)
  # Filter DataFrame for the relevant education levels and ATBANI1 variable
  df_filtered_atbani1 <- df[df$ATBANI1 %in% c(0, 1) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atbani1$Education_Level <- ifelse(df_filtered_atbani1$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_atbani1 <- table(df_filtered_atbani1$ATBANI1, df_filtered_atbani1$Education_Level)
# Add descriptive labels to the rows and columns
rownames(table_atbani1) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_atbani1 <- chisq.test(table_atbani1)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani1 <- oddsratio(table_atbani1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani1, caption = "Contingency Table: Education Level vs. Exchanging Resistant Bacteria with Pets (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani1)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani1)

---------------------------------------------------------------------------------------------------------------------
  
  ### ATBANI2=The use of antibiotics in livestock and crops can increase the 
  #presence of resistant bacteria in the environment (False=14.7%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Filter DataFrame for the relevant education levels and ATBANI2 variable
df_filtered_atbani2 <- df[df$ATBANI2 %in% c(0, 1) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atbani2$Education_Level <- ifelse(df_filtered_atbani2$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_atbani2 <- table(df_filtered_atbani2$ATBANI2, df_filtered_atbani2$Education_Level)
# Add descriptive labels to the rows and columns
rownames(table_atbani2) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_atbani2 <- chisq.test(table_atbani2)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani2 <- oddsratio(table_atbani2, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani2, caption = "Contingency Table: Education Level vs. Antibiotics in Livestock and Crops Affecting Environment (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani2)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani2)


--------------------------------------------------------------------------------------------------------------------
  
  ##### ATBANI3	The use of antibiotics in livestock and crops can affect me directly
  ##(I can get resistant bacteria in my body) (False=26.3%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
df <- Database_simplified  
# Filter DataFrame for the relevant education levels and ATBANI3 variable
df_filtered_atbani3 <- df[df$ATBANI3 %in% c(0, 1) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atbani3$Education_Level <- ifelse(df_filtered_atbani3$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_atbani3 <- table(df_filtered_atbani3$ATBANI3, df_filtered_atbani3$Education_Level)
# Add descriptive labels to the rows and columns
rownames(table_atbani3) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_atbani3 <- chisq.test(table_atbani3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani3 <- oddsratio(table_atbani3, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani3, caption = "Contingency Table: Education Level vs. Antibiotics in Livestock and Crops Affecting Humans Directly (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani3)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani3)

-------------------------------------------------------------------------------------------------------------------
  ##### ATBANI4	Resistant bacteria are only found in hospitals (True=10.8%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
df <- Database_simplified  
df_filtered_atbani4 <- df[df$ATBANI4 %in% c(0, 1) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atbani4$Education_Level <- ifelse(df_filtered_atbani4$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_atbani4 <- table(df_filtered_atbani4$ATBANI4, df_filtered_atbani4$Education_Level)
rownames(table_atbani4) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_atbani4 <- chisq.test(table_atbani4)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani4 <- oddsratio(table_atbani4, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani4, caption = "Contingency Table: Education Level vs. Resistant Bacteria Found Only in Hospitals (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani4)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani4)

----------------------------------------------------------------------------------------------------------------------
  
  #####RESATB1	Antibiotic resistance occurs when your body becomes resistant to antibiotics and they
  ##no longer work as well (True=58.3%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
df <- Database_simplified  
df_filtered_resatb1 <- df[df$RESATB1 %in% c(0, 1) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resatb1$Education_Level <- ifelse(df_filtered_resatb1$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_resatb1 <- table(df_filtered_resatb1$RESATB1, df_filtered_resatb1$Education_Level)
rownames(table_resatb1) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_resatb1 <- chisq.test(table_resatb1)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb1 <- oddsratio(table_resatb1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb1, caption = "Contingency Table: Education Level vs. Understanding of Antibiotic Resistance (RESATB1: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb1)
print(odds_ratio_resatb1)

-------------------------------------------------------------------------------------------------------------------
  
  #####RESATB2	Many infections are becoming increasingly resistant to antibiotic treatment  (False=12.5%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb2 <- df[df$RESATB2 %in% c(0, 1) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resatb2$Education_Level <- ifelse(df_filtered_resatb2$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_resatb2 <- table(df_filtered_resatb2$RESATB2, df_filtered_resatb2$Education_Level)
rownames(table_resatb2) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_resatb2 <- chisq.test(table_resatb2)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb2 <- oddsratio(table_resatb2, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb2, caption = "Contingency Table: Education Level vs. Perception of Increasing Infection Resistance (RESATB2: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb2)
print(odds_ratio_resatb2)

---------------------------------------------------------------------------------------------------------------------
  #####RESATB3	If bacteria are resistant to antibiotics, it can be very difficult or impossible to treat the infections they cause (False=16.7%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb3 <- df[df$RESATB3 %in% c(0, 1) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resatb3$Education_Level <- ifelse(df_filtered_resatb3$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_resatb3 <- table(df_filtered_resatb3$RESATB3, df_filtered_resatb3$Education_Level)
rownames(table_resatb3) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_resatb3 <- chisq.test(table_resatb3)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb3 <- oddsratio(table_resatb3, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb3, caption = "Contingency Table: Education Level vs. Perception of Difficulty Treating Infections (RESATB3: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb3)
print(odds_ratio_resatb3)
----------------------------------------------------------------------------------------------------------------------
  #####RESATB4	Antibiotic resistance is an issue that could affect me or my family (False=11.8%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb4 <- df[df$RESATB4 %in% c(0, 1) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resatb4$Education_Level <- ifelse(df_filtered_resatb4$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_resatb4 <- table(df_filtered_resatb4$RESATB4, df_filtered_resatb4$Education_Level)
rownames(table_resatb4) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_resatb4 <- chisq.test(table_resatb4)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb4 <- oddsratio(table_resatb4, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb4, caption = "Contingency Table: Education Level vs. Perception of Antibiotic Resistance Affecting One's Family (RESATB4: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb4)
print(odds_ratio_resatb4)

---------------------------------------------------------------------------------------------------------------------
  #####RESATB5	Antibiotic resistance is an issue in other countries but not here (True=9.9%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb5 <- df[df$RESATB5 %in% c(0, 1) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resatb5$Education_Level <- ifelse(df_filtered_resatb5$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_resatb5 <- table(df_filtered_resatb5$RESATB5, df_filtered_resatb5$Education_Level)
rownames(table_resatb5) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_resatb5 <- chisq.test(table_resatb5)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb5 <- oddsratio(table_resatb5, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb5, caption = "Contingency Table: Education Level vs. Perception of Antibiotic Resistance as an Issue Only in Other Countries (RESATB5: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb5)
print(odds_ratio_resatb5)
---------------------------------------------------------------------------------------------------------------------  
  
  #####RESATB6	Antibiotic resistance is only a problem for people who take antibiotics regularly (True=17.5%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb6 <- df[df$RESATB6 %in% c(0, 1) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resatb6$Education_Level <- ifelse(df_filtered_resatb6$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_resatb6 <- table(df_filtered_resatb6$RESATB6, df_filtered_resatb6$Education_Level)
rownames(table_resatb6) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_resatb6 <- chisq.test(table_resatb6)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb6 <- oddsratio(table_resatb6, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb6, caption = "Contingency Table: Education Level vs. Perception of Antibiotic Resistance as a Problem Only for Regular Antibiotic Users (RESATB6: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb6)
print(odds_ratio_resatb6)

--------------------------------------------------------------------------------------------------------------------- 
  #####RESATB7	Bacteria that are resistant to antibiotics can be spread from person to person (False=20.2%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb7 <- df[df$RESATB7 %in% c(0, 1) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resatb7$Education_Level <- ifelse(df_filtered_resatb7$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_resatb7 <- table(df_filtered_resatb7$RESATB7, df_filtered_resatb7$Education_Level)
rownames(table_resatb7) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_resatb7 <- chisq.test(table_resatb7)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb7 <- oddsratio(table_resatb7, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb7, caption = "Contingency Table: Education Level vs. Perception of Bacteria Transmission Person to Person (RESATB7: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb7)
print(odds_ratio_resatb7)

--------------------------------------------------------------------------------------------------------------------
  #####RESATB8	Antibiotic-resistant infections could make medical procedures like surgery, organ transplants,
  ##and cancer treatment much more dangerous (False=12.0%)
  
  # Load the database
  df <- Database_simplified
df_filtered_resatb8 <- df[df$RESATB8 %in% c(0, 1) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resatb8$Education_Level <- ifelse(df_filtered_resatb8$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_resatb8 <- table(df_filtered_resatb8$RESATB8, df_filtered_resatb8$Education_Level)
rownames(table_resatb8) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_resatb8 <- chisq.test(table_resatb8)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb8 <- oddsratio(table_resatb8, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb8, caption = "Contingency Table: Education Level vs. Perception of Antibiotic-Resistant Infections and Medical Procedures (RESATB8: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb8)
print(odds_ratio_resatb8)

--------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL1	Farmers should give fewer antibiotics to food-producing animals 
  
  ##################### 1st scenario (Strongly desagree=8.68%) vs. Strongly Agree
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl1_scenario1 <- df[df$ATBRGL1 %in% c(1, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atbrgl1_scenario1$Education_Level <- ifelse(df_filtered_atbrgl1_scenario1$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_atbrgl1_scenario1 <- table(df_filtered_atbrgl1_scenario1$ATBRGL1, df_filtered_atbrgl1_scenario1$Education_Level)
rownames(table_atbrgl1_scenario1) <- c("Strongly Disagree", "Strongly Agree")
# Perform the Chi-Squared test
chi_result_atbrgl1_scenario1 <- chisq.test(table_atbrgl1_scenario1)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl1_scenario1 <- oddsratio(table_atbrgl1_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl1_scenario1, caption = "Contingency Table: Education Level vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_atbrgl1_scenario1)
print(odds_ratio_atbrgl1_scenario1)

############################# 2nd scenario Farmers should give fewer antibiotics to
##food-producing animals (Neither agree nor desagree=22.6%) vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl1_scenario2 <- df[df$ATBRGL1 %in% c(2, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atbrgl1_scenario2$Education_Level <- ifelse(df_filtered_atbrgl1_scenario2$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_atbrgl1_scenario2 <- table(df_filtered_atbrgl1_scenario2$ATBRGL1, df_filtered_atbrgl1_scenario2$Education_Level)
rownames(table_atbrgl1_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
# Perform the Chi-Squared test
chi_result_atbrgl1_scenario2 <- chisq.test(table_atbrgl1_scenario2)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl1_scenario2 <- oddsratio(table_atbrgl1_scenario2, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl1_scenario2, caption = "Contingency Table: Education Level vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Neither Agree Nor Disagree)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_atbrgl1_scenario2)
print(odds_ratio_atbrgl1_scenario2)

############################# 3rd scenario (Strongly desagree + Neither agree nor desagree=31.28%) vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl1_scenario3 <- df[df$ATBRGL1 %in% c(1, 2, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atbrgl1_scenario3$Education_Level <- ifelse(df_filtered_atbrgl1_scenario3$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
df_filtered_atbrgl1_scenario3$Disagree_Neither <- df_filtered_atbrgl1_scenario3$ATBRGL1 %in% c(1, 2)
table_atbrgl1_scenario3 <- table(df_filtered_atbrgl1_scenario3$Disagree_Neither, df_filtered_atbrgl1_scenario3$Education_Level)
rownames(table_atbrgl1_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
# Perform the Chi-Squared test
chi_result_atbrgl1_scenario3 <- chisq.test(table_atbrgl1_scenario3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl1_scenario3 <- oddsratio(table_atbrgl1_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl1_scenario3, caption = "Contingency Table: Education Level vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree + Neither)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_atbrgl1_scenario3)
print(odds_ratio_atbrgl1_scenario3)

--------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL2	People should not keep antibiotics and use them later for other illnesses  
  
  ############################# 1st scenario Strongly desagree vs. Strongly Agree
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the database
df <- Database_simplified
## Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_atbrgl2_scenario1 <- df[df$ATBRGL2 %in% c(1, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atbrgl2_scenario1$Education_Level <- ifelse(df_filtered_atbrgl2_scenario1$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_atbrgl2_scenario1 <- table(df_filtered_atbrgl2_scenario1$ATBRGL2, df_filtered_atbrgl2_scenario1$Education_Level)
rownames(table_atbrgl2_scenario1) <- c("Strongly Disagree", "Strongly Agree")
# Perform Chi-Squared test
chi_result_atbrgl2_scenario1 <- chisq.test(table_atbrgl2_scenario1)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl2_scenario1 <- oddsratio(table_atbrgl2_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl2_scenario1, caption = "Contingency Table: Education Level vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl2_scenario1)
print(odds_ratio_atbrgl2_scenario1)

############################# 2nd scenario Neither agree nor desagree vs. Strongly Agree
# Filter for 'Strongly Agree' (3) and 'Neither Agree Nor Disagree' (2) responses for ATBRGL2
df_filtered_atbrgl2_scenario2 <- df[df$ATBRGL2 %in% c(2, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atbrgl2_scenario2$Education_Level <- ifelse(df_filtered_atbrgl2_scenario2$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_atbrgl2_scenario2 <- table(df_filtered_atbrgl2_scenario2$ATBRGL2, df_filtered_atbrgl2_scenario2$Education_Level)
rownames(table_atbrgl2_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
# Perform Chi-Squared test
chi_result_atbrgl2_scenario2 <- chisq.test(table_atbrgl2_scenario2)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl2_scenario2 <- oddsratio(table_atbrgl2_scenario2, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl2_scenario2, caption = "Contingency Table: Education Level vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl2_scenario2)
print(odds_ratio_atbrgl2_scenario2)


############################# 3rd scenario Neither agree nor desagree + Stringly Disagree vs. Strongly Agree
df_filtered_atbrgl2_scenario3 <- df[df$ATBRGL2 %in% c(1, 2, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atbrgl2_scenario3$Education_Level <- ifelse(df_filtered_atbrgl2_scenario3$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
df_filtered_atbrgl2_scenario3$Disagree_Neither <- df_filtered_atbrgl2_scenario3$ATBRGL2 %in% c(1, 2)
table_atbrgl2_scenario3 <- table(df_filtered_atbrgl2_scenario3$Disagree_Neither, df_filtered_atbrgl2_scenario3$Education_Level)
rownames(table_atbrgl2_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
# Perform the Chi-Squared test
chi_result_atbrgl2_scenario3 <- chisq.test(table_atbrgl2_scenario3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl2_scenario3 <- oddsratio(table_atbrgl2_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl2_scenario3, caption = "Contingency Table: Education Level vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl2_scenario3)
print(odds_ratio_atbrgl2_scenario3)

--------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL3 Parents should make sure all of their children’s vaccinations are up-to-date 
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)

####1st scenario
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl3_scenario1 <- df[df$ATBRGL3 %in% c(1, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atbrgl3_scenario1$Education_Level <- ifelse(df_filtered_atbrgl3_scenario1$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_atbrgl3_scenario1 <- table(df_filtered_atbrgl3_scenario1$ATBRGL3, df_filtered_atbrgl3_scenario1$Education_Level)
rownames(table_atbrgl3_scenario1) <- c("Strongly Disagree", "Strongly Agree")
# Perform Chi-Squared test
chi_result_atbrgl3_scenario1 <- chisq.test(table_atbrgl3_scenario1)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl3_scenario1 <- oddsratio(table_atbrgl3_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl3_scenario1, caption = "Contingency Table: Education Level vs. Opinion on Children's Vaccinations (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl3_scenario1)
print(odds_ratio_atbrgl3_scenario1)

### 2nd Scenario
df_filtered_atbrgl3_scenario2 <- df[df$ATBRGL3 %in% c(2, 3) & df$AGE %in% c(1, 2, 3, 4, 5, 6), ]
df_filtered_atbrgl3_scenario2 <- df[df$ATBRGL3 %in% c(2, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atbrgl3_scenario2$Education_Level <- ifelse(df_filtered_atbrgl3_scenario2$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_atbrgl3_scenario2 <- table(df_filtered_atbrgl3_scenario2$ATBRGL3, df_filtered_atbrgl3_scenario2$Education_Level)
rownames(table_atbrgl3_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
# Perform Chi-Squared test
chi_result_atbrgl3_scenario2 <- chisq.test(table_atbrgl3_scenario2)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl3_scenario2 <- oddsratio(table_atbrgl3_scenario2, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl3_scenario2, caption = "Contingency Table: Education Level vs. Opinion on Children's Vaccinations (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl3_scenario2)
print(odds_ratio_atbrgl3_scenario2)

## 3rd scenario
df_filtered_atbrgl3_scenario3 <- df[df$ATBRGL3 %in% c(1, 2, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atbrgl3_scenario3$Education_Level <- ifelse(df_filtered_atbrgl3_scenario3$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
df_filtered_atbrgl3_scenario3$Disagree_Neither <- df_filtered_atbrgl3_scenario3$ATBRGL3 %in% c(1, 2)
table_atbrgl3_scenario3 <- table(df_filtered_atbrgl3_scenario3$Disagree_Neither, df_filtered_atbrgl3_scenario3$Education_Level)
rownames(table_atbrgl3_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
# Perform the Chi-Squared test
chi_result_atbrgl3_scenario3 <- chisq.test(table_atbrgl3_scenario3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl3_scenario3 <- oddsratio(table_atbrgl3_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl3_scenario3, caption = "Contingency Table: Education Level vs. Opinion on Children's Vaccinations (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl3_scenario3)
print(odds_ratio_atbrgl3_scenario3)

---------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL4 People should wash their hands regularly
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

## Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_atbrgl4_scenario1 <- df[df$ATBRGL4 %in% c(1, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atbrgl4_scenario1$Education_Level <- ifelse(df_filtered_atbrgl4_scenario1$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_atbrgl4_scenario1 <- table(df_filtered_atbrgl4_scenario1$ATBRGL4, df_filtered_atbrgl4_scenario1$Education_Level)
rownames(table_atbrgl4_scenario1) <- c("Strongly Disagree", "Strongly Agree")
chi_result_atbrgl4_scenario1 <- chisq.test(table_atbrgl4_scenario1)
odds_ratio_atbrgl4_scenario1 <- oddsratio(table_atbrgl4_scenario1, conf.level = 0.95)$measure
print(kable(table_atbrgl4_scenario1, caption = "Contingency Table: Education Level vs. Hand Washing Importance (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl4_scenario1)
print(odds_ratio_atbrgl4_scenario1)

## Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl4_scenario2 <- df[df$ATBRGL4 %in% c(2, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atbrgl4_scenario2$Education_Level <- ifelse(df_filtered_atbrgl4_scenario2$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_atbrgl4_scenario2 <- table(df_filtered_atbrgl4_scenario2$ATBRGL4, df_filtered_atbrgl4_scenario2$Education_Level)
rownames(table_atbrgl4_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
chi_result_atbrgl4_scenario2 <- chisq.test(table_atbrgl4_scenario2)
odds_ratio_atbrgl4_scenario2 <- oddsratio(table_atbrgl4_scenario2, conf.level = 0.95)$measure
print(kable(table_atbrgl4_scenario2, caption = "Contingency Table: Education Level vs. Hand Washing Importance (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl4_scenario2)
print(odds_ratio_atbrgl4_scenario2)

## Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl4_scenario3 <- df[df$ATBRGL4 %in% c(1, 2, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atbrgl4_scenario3$Education_Level <- ifelse(df_filtered_atbrgl4_scenario3$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
df_filtered_atbrgl4_scenario3$Disagree_Neither <- df_filtered_atbrgl4_scenario3$ATBRGL4 %in% c(1, 2)
table_atbrgl4_scenario3 <- table(df_filtered_atbrgl4_scenario3$Disagree_Neither, df_filtered_atbrgl4_scenario3$Education_Level)
rownames(table_atbrgl4_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
chi_result_atbrgl4_scenario3 <- chisq.test(table_atbrgl4_scenario3)
odds_ratio_atbrgl4_scenario3 <- oddsratio(table_atbrgl4_scenario3, conf.level = 0.95)$measure
print(kable(table_atbrgl4_scenario3, caption = "Contingency Table: Education Level vs. Hand Washing Importance (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl4_scenario3)
print(odds_ratio_atbrgl4_scenario3)

---------------------------------------------------------------------------------------------------------------------
  
  #ATBRGL5 Doctors should only prescribe antibiotics when they are needed 
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)

# Load the Database_simplified dataframe
df <- Database_simplified

## Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_atbrgl5_scenario1 <- df[df$ATBRGL5 %in% c(1, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atbrgl5_scenario1$Education_Level <- ifelse(df_filtered_atbrgl5_scenario1$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_atbrgl5_scenario1 <- table(df_filtered_atbrgl5_scenario1$ATBRGL5, df_filtered_atbrgl5_scenario1$Education_Level)
rownames(table_atbrgl5_scenario1) <- c("Strongly Disagree", "Strongly Agree")
chi_result_atbrgl5_scenario1 <- chisq.test(table_atbrgl5_scenario1)
odds_ratio_atbrgl5_scenario1 <- oddsratio(table_atbrgl5_scenario1, conf.level = 0.95)$measure
print(kable(table_atbrgl5_scenario1, caption = "Contingency Table: Education Level vs. Antibiotic Prescription Necessity (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl5_scenario1)
print(odds_ratio_atbrgl5_scenario1)

## Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl5_scenario2 <- df[df$ATBRGL5 %in% c(2, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atbrgl5_scenario2$Education_Group <- ifelse(df_filtered_atbrgl5_scenario2$NIVSCOL %in% c(7, 8), "Higher Education", "Others")
table_atbrgl5_scenario2 <- table(df_filtered_atbrgl5_scenario2$ATBRGL5, df_filtered_atbrgl5_scenario2$Education_Group)
rownames(table_atbrgl5_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
chi_result_atbrgl5_scenario2 <- chisq.test(table_atbrgl5_scenario2)
odds_ratio_atbrgl5_scenario2 <- oddsratio(table_atbrgl5_scenario2, conf.level = 0.95)$measure
print(kable(table_atbrgl5_scenario2, caption = "Contingency Table: Education Level vs. Antibiotic Prescription Necessity (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl5_scenario2)
print(odds_ratio_atbrgl5_scenario2)

## Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl5_scenario3 <- df[df$ATBRGL5 %in% c(1, 2, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atbrgl5_scenario3$Education_Group <- ifelse(df_filtered_atbrgl5_scenario3$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
df_filtered_atbrgl5_scenario3$Disagree_Neither <- df_filtered_atbrgl5_scenario3$ATBRGL5 %in% c(1, 2)
table_atbrgl5_scenario3 <- table(df_filtered_atbrgl5_scenario3$Disagree_Neither, df_filtered_atbrgl5_scenario3$Education_Group)
rownames(table_atbrgl5_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
chi_result_atbrgl5_scenario3 <- chisq.test(table_atbrgl5_scenario3)
odds_ratio_atbrgl5_scenario3 <- oddsratio(table_atbrgl5_scenario3, conf.level = 0.95)$measure
print(kable(table_atbrgl5_scenario3, caption = "Contingency Table: Education Level vs. Antibiotic Prescription Necessity (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl5_scenario3)
print(odds_ratio_atbrgl5_scenario3)

----------------------------------------------------------------------------------------------------------------------
  
  ##ATBRGL6= People should only use antibiotics when prescribed by a doctor or nurse
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

## Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_atbrgl6_scenario1 <- df[df$ATBRGL6 %in% c(1, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atbrgl6_scenario1$Education_Group <- ifelse(df_filtered_atbrgl6_scenario1$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_atbrgl6_scenario1 <- table(df_filtered_atbrgl6_scenario1$ATBRGL6, df_filtered_atbrgl6_scenario1$Education_Group)
rownames(table_atbrgl6_scenario1) <- c("Strongly Disagree", "Strongly Agree")
chi_result_atbrgl6_scenario1 <- chisq.test(table_atbrgl6_scenario1)
odds_ratio_atbrgl6_scenario1 <- oddsratio(table_atbrgl6_scenario1, conf.level = 0.95)$measure
print(kable(table_atbrgl6_scenario1, caption = "Contingency Table: Education Level vs. Antibiotic only when prescribed (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl6_scenario1)
print(odds_ratio_atbrgl6_scenario1)

## Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl6_scenario2 <- df[df$ATBRGL6 %in% c(2, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atbrgl6_scenario2$Education_Group <- ifelse(df_filtered_atbrgl6_scenario2$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_atbrgl6_scenario2 <- table(df_filtered_atbrgl6_scenario2$ATBRGL6, df_filtered_atbrgl6_scenario2$Education_Group)
rownames(table_atbrgl6_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
chi_result_atbrgl6_scenario2 <- chisq.test(table_atbrgl6_scenario2)
odds_ratio_atbrgl6_scenario2 <- oddsratio(table_atbrgl6_scenario2, conf.level = 0.95)$measure
print(kable(table_atbrgl6_scenario2, caption = "Contingency Table: Education Level vs. Antibiotic only when prescribed (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl6_scenario2)
print(odds_ratio_atbrgl6_scenario2)

## Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_atbrgl6_scenario3 <- df[df$ATBRGL6 %in% c(1, 2, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_atbrgl6_scenario3$Education_Group <- ifelse(df_filtered_atbrgl6_scenario3$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
df_filtered_atbrgl6_scenario3$Disagree_Neither <- df_filtered_atbrgl6_scenario3$ATBRGL6 %in% c(1, 2)
table_atbrgl6_scenario3 <- table(df_filtered_atbrgl6_scenario3$Disagree_Neither, df_filtered_atbrgl6_scenario3$Education_Group)
rownames(table_atbrgl6_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
chi_result_atbrgl6_scenario3 <- chisq.test(table_atbrgl6_scenario3)
odds_ratio_atbrgl6_scenario3 <- oddsratio(table_atbrgl6_scenario3, conf.level = 0.95)$measure
print(kable(table_atbrgl6_scenario3, caption = "Contingency Table: Education Level vs. Antibiotic only when prescribed (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl6_scenario3)
print(odds_ratio_atbrgl6_scenario3)

----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM1= Antibiotic resistance is one of the biggest problems the world faces
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_resdim1_scenario1 <- df[df$RESDIM1 %in% c(1, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resdim1_scenario1$Education_Group <- ifelse(df_filtered_resdim1_scenario1$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_resdim1_scenario1 <- table(df_filtered_resdim1_scenario1$RESDIM1, df_filtered_resdim1_scenario1$Education_Group)
rownames(table_resdim1_scenario1) <- c("Strongly Disagree", "Strongly Agree")
chi_result_resdim1_scenario1 <- chisq.test(table_resdim1_scenario1)
odds_ratio_resdim1_scenario1 <- oddsratio(table_resdim1_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim1_scenario1, caption = "Contingency Table: Education Level vs. Perception of Antibiotic Resistance as a Global Problem (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_resdim1_scenario1)
print(odds_ratio_resdim1_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim1_scenario2 <- df[df$RESDIM1 %in% c(2, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resdim1_scenario2$Education_Group <- ifelse(df_filtered_resdim1_scenario2$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_resdim1_scenario2 <- table(df_filtered_resdim1_scenario2$RESDIM1, df_filtered_resdim1_scenario2$Education_Group)
rownames(table_resdim1_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
chi_result_resdim1_scenario2 <- chisq.test(table_resdim1_scenario2)
odds_ratio_resdim1_scenario2 <- oddsratio(table_resdim1_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim1_scenario2, caption = "Contingency Table: Education Level vs. Perception of Antibiotic Resistance as a Global Problem (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim1_scenario2)
print(odds_ratio_resdim1_scenario2)

# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim1_scenario3 <- df[df$RESDIM1 %in% c(1, 2, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resdim1_scenario3$Education_Group <- ifelse(df_filtered_resdim1_scenario3$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
df_filtered_resdim1_scenario3$Disagree_Neither <- df_filtered_resdim1_scenario3$RESDIM1 %in% c(1, 2)
table_resdim1_scenario3 <- table(df_filtered_resdim1_scenario3$Disagree_Neither, df_filtered_resdim1_scenario3$Education_Group)
rownames(table_resdim1_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
chi_result_resdim1_scenario3 <- chisq.test(table_resdim1_scenario3)
odds_ratio_resdim1_scenario3 <- oddsratio(table_resdim1_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim1_scenario3, caption = "Contingency Table: Education Level vs. Perception of Antibiotic Resistance as a Global Problem (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_resdim1_scenario3)
print(odds_ratio_resdim1_scenario3)

----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM2= Medical experts will solve the problem of antibiotic resistance before it becomes too serious 
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Load the Database_simplified dataframe
df <- read_excel("C:/Database_simplified.xlsx")

# Scenario 1: Strongly Agree vs. Strongly Disagree
df_filtered_resdim2_scenario1 <- df[df$RESDIM2 %in% c(1, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resdim2_scenario1$Education_Group <- ifelse(df_filtered_resdim2_scenario1$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_resdim2_scenario1 <- table(df_filtered_resdim2_scenario1$RESDIM2, df_filtered_resdim2_scenario1$Education_Group)
rownames(table_resdim2_scenario1) <- c("Strongly Disagree", "Strongly Agree")
chi_result_resdim2_scenario1 <- chisq.test(table_resdim2_scenario1)
odds_ratio_resdim2_scenario1 <- oddsratio(table_resdim2_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim2_scenario1, caption = "Contingency Table: Education Level vs. Belief in Solving Antibiotic Resistance (Strongly Disagree vs. Strongly Agree)"))
print(chi_result_resdim2_scenario1)
print(odds_ratio_resdim2_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim2_scenario2 <- df[df$RESDIM2 %in% c(1, 2) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resdim2_scenario2$Education_Group <- ifelse(df_filtered_resdim2_scenario2$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_resdim2_scenario2 <- table(df_filtered_resdim2_scenario2$RESDIM2, df_filtered_resdim2_scenario2$Education_Group)
rownames(table_resdim2_scenario2) <- c("Strongly Disagree", "Neither Agree Nor Disagree")
chi_result_resdim2_scenario2 <- chisq.test(table_resdim2_scenario2)
odds_ratio_resdim2_scenario2 <- oddsratio(table_resdim2_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim2_scenario2, caption = "Contingency Table: Education Level vs. Belief in Solving Antibiotic Resistance (Strongly Disagree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim2_scenario2)
print(odds_ratio_resdim2_scenario2)

# Scenario 3: Strongly Agree + Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim2_scenario3 <- df[df$RESDIM2 %in% c(1, 2, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resdim2_scenario3$Education_Group <- ifelse(df_filtered_resdim2_scenario3$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
df_filtered_resdim2_scenario3$Agree_Neither <- df_filtered_resdim2_scenario3$RESDIM2 %in% c(2, 3)
table_resdim2_scenario3 <- table(df_filtered_resdim2_scenario3$Agree_Neither, df_filtered_resdim2_scenario3$Education_Group)
rownames(table_resdim2_scenario3) <- c("Strongly Disagree", "Strongly Agree + Neither")
chi_result_resdim2_scenario3 <- chisq.test(table_resdim2_scenario3)
odds_ratio_resdim2_scenario3 <- oddsratio(table_resdim2_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim2_scenario3, caption = "Contingency Table: Education Level vs. Belief in Solving Antibiotic Resistance (Strongly Disagree vs. Strongly Agree + Neither Agree Nor Disagree)"))
print(chi_result_resdim2_scenario3)
print(odds_ratio_resdim2_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM3= Everyone needs to use antibiotics responsibly
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_resdim3_scenario1 <- df[df$RESDIM3 %in% c(1, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resdim3_scenario1$Education_Group <- ifelse(df_filtered_resdim3_scenario1$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_resdim3_scenario1 <- table(df_filtered_resdim3_scenario1$RESDIM3, df_filtered_resdim3_scenario1$Education_Group)
rownames(table_resdim3_scenario1) <- c("Strongly Disagree", "Strongly Agree")
chi_result_resdim3_scenario1 <- chisq.test(table_resdim3_scenario1)
odds_ratio_resdim3_scenario1 <- oddsratio(table_resdim3_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim3_scenario1, caption = "Contingency Table: Education Level vs. Everyone needs to use antibiotics responsibly (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_resdim3_scenario1)
print(odds_ratio_resdim3_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim3_scenario2 <- df[df$RESDIM3 %in% c(2, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resdim3_scenario2$Education_Group <- ifelse(df_filtered_resdim3_scenario2$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_resdim3_scenario2 <- table(df_filtered_resdim3_scenario2$RESDIM3, df_filtered_resdim3_scenario2$Education_Group)
rownames(table_resdim3_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
chi_result_resdim3_scenario2 <- chisq.test(table_resdim3_scenario2)
odds_ratio_resdim3_scenario2 <- oddsratio(table_resdim3_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim3_scenario2, caption = "Contingency Table: Education Level vs. Everyone needs to use antibiotics responsibly (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim3_scenario2)
print(odds_ratio_resdim3_scenario2)

# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim3_scenario3 <- df[df$RESDIM3 %in% c(1, 2, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resdim3_scenario3$Education_Group <- ifelse(df_filtered_resdim3_scenario3$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
df_filtered_resdim3_scenario3$Disagree_Neither <- df_filtered_resdim3_scenario3$RESDIM3 %in% c(1, 2)
table_resdim3_scenario3 <- table(df_filtered_resdim3_scenario3$Disagree_Neither, df_filtered_resdim3_scenario3$Education_Group)
rownames(table_resdim3_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
chi_result_resdim3_scenario3 <- chisq.test(table_resdim3_scenario3)
odds_ratio_resdim3_scenario3 <- oddsratio(table_resdim3_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim3_scenario3, caption = "Contingency Table: Education Level vs. Everyone needs to use antibiotics responsibly (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_resdim3_scenario3)
print(odds_ratio_resdim3_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM4= People like me can't do much to stop antibiotic resistance
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Agree vs. Strongly Disagree
df_filtered_resdim4_scenario1 <- df[df$RESDIM4 %in% c(1, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resdim4_scenario1$Education_Group <- ifelse(df_filtered_resdim4_scenario1$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_resdim4_scenario1 <- table(df_filtered_resdim4_scenario1$RESDIM4, df_filtered_resdim4_scenario1$Education_Group)
rownames(table_resdim4_scenario1) <- c("Strongly Disagree", "Strongly Agree")
chi_result_resdim4_scenario1 <- chisq.test(table_resdim4_scenario1)
odds_ratio_resdim4_scenario1 <- oddsratio(table_resdim4_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim4_scenario1, caption = "Contingency Table: Education Level vs. Belief in Individual Impact on Antibiotic Resistance (Strongly Disagree vs. Strongly Agree)"))
print(chi_result_resdim4_scenario1)
print(odds_ratio_resdim4_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim4_scenario2 <- df[df$RESDIM4 %in% c(1, 2) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resdim4_scenario2$Education_Group <- ifelse(df_filtered_resdim4_scenario2$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_resdim4_scenario2 <- table(df_filtered_resdim4_scenario2$RESDIM4, df_filtered_resdim4_scenario2$Education_Group)
rownames(table_resdim4_scenario2) <- c("Strongly Disagree", "Neither Agree Nor Disagree")
chi_result_resdim4_scenario2 <- chisq.test(table_resdim4_scenario2)
odds_ratio_resdim4_scenario2 <- oddsratio(table_resdim4_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim4_scenario2, caption = "Contingency Table: Education Level vs. Belief in Individual Impact on Antibiotic Resistance (Strongly Disagree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim4_scenario2)
print(odds_ratio_resdim4_scenario2)

# Scenario 3: Strongly Agree + Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim4_scenario3 <- df[df$RESDIM4 %in% c(1, 2, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resdim4_scenario3$Education_Group <- ifelse(df_filtered_resdim4_scenario3$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
df_filtered_resdim4_scenario3$Agree_Neither <- df_filtered_resdim4_scenario3$RESDIM4 %in% c(2, 3)
table_resdim4_scenario3 <- table(df_filtered_resdim4_scenario3$Agree_Neither, df_filtered_resdim4_scenario3$Education_Group)
rownames(table_resdim4_scenario3) <- c("Strongly Disagree", "Strongly Agree + Neither")
chi_result_resdim4_scenario3 <- chisq.test(table_resdim4_scenario3)
odds_ratio_resdim4_scenario3 <- oddsratio(table_resdim4_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim4_scenario3, caption = "Contingency Table: Education Level vs. Belief in Individual Impact on Antibiotic Resistance (Strongly Disagree vs. Strongly Agree + Neither Agree Nor Disagree)"))
print(chi_result_resdim4_scenario3)
print(odds_ratio_resdim4_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM5= I am worried about the impact that antibiotic resistance will have on my health and that of my family
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_resdim5_scenario1 <- df[df$RESDIM5 %in% c(1, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resdim5_scenario1$Education_Group <- ifelse(df_filtered_resdim5_scenario1$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_resdim5_scenario1 <- table(df_filtered_resdim5_scenario1$RESDIM5, df_filtered_resdim5_scenario1$Education_Group)
rownames(table_resdim5_scenario1) <- c("Strongly Disagree", "Strongly Agree")
chi_result_resdim5_scenario1 <- chisq.test(table_resdim5_scenario1)
odds_ratio_resdim5_scenario1 <- oddsratio(table_resdim5_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim5_scenario1, caption = "Contingency Table: Education Level vs. Impact of AMR on personal health and that of their family (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_resdim5_scenario1)
print(odds_ratio_resdim5_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim5_scenario2 <- df[df$RESDIM5 %in% c(2, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resdim5_scenario2$Education_Group <- ifelse(df_filtered_resdim5_scenario2$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_resdim5_scenario2 <- table(df_filtered_resdim5_scenario2$RESDIM5, df_filtered_resdim5_scenario2$Education_Group)
rownames(table_resdim5_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
chi_result_resdim5_scenario2 <- chisq.test(table_resdim5_scenario2)
odds_ratio_resdim5_scenario2 <- oddsratio(table_resdim5_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim5_scenario2, caption = "Contingency Table: Education Level vs. Impact of AMR on personal health and that of their family (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim5_scenario2)
print(odds_ratio_resdim5_scenario2)

# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
df_filtered_resdim5_scenario3 <- df[df$RESDIM5 %in% c(1, 2, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resdim5_scenario3$Education_Group <- ifelse(df_filtered_resdim5_scenario3$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
df_filtered_resdim5_scenario3$Disagree_Neither <- df_filtered_resdim5_scenario3$RESDIM5 %in% c(1, 2)
table_resdim5_scenario3 <- table(df_filtered_resdim5_scenario3$Disagree_Neither, df_filtered_resdim5_scenario3$Education_Group)
rownames(table_resdim5_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
chi_result_resdim5_scenario3 <- chisq.test(table_resdim5_scenario3)
odds_ratio_resdim5_scenario3 <- oddsratio(table_resdim5_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim5_scenario3, caption = "Contingency Table: Education Level vs. Impact of AMR on personal health and that of their family (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_resdim5_scenario3)
print(odds_ratio_resdim5_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM6= I am not at risk of getting an antibiotic-resistant infection, as long as I take my antibiotics correctly
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Agree vs. Strongly Disagree
df_filtered_resdim6_scenario1 <- df[df$RESDIM6 %in% c(1, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resdim6_scenario1$Education_Group <- ifelse(df_filtered_resdim6_scenario1$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_resdim6_scenario1 <- table(df_filtered_resdim6_scenario1$RESDIM6, df_filtered_resdim6_scenario1$Education_Group)
rownames(table_resdim6_scenario1) <- c("Strongly Disagree", "Strongly Agree")
chi_result_resdim6_scenario1 <- chisq.test(table_resdim6_scenario1)
odds_ratio_resdim6_scenario1 <- oddsratio(table_resdim6_scenario1, conf.level = 0.95)$measure
print(knitr::kable(table_resdim6_scenario1, caption = "Contingency Table: Education Level vs. Perception of Risk of Antibiotic-Resistant Infection (Strongly Disagree vs. Strongly Agree)"))
print(chi_result_resdim6_scenario1)
print(odds_ratio_resdim6_scenario1)
print(table_resdim6_scenario1)

# Scenario 2: Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim6_scenario2 <- df[df$RESDIM6 %in% c(1, 2) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resdim6_scenario2$Education_Group <- ifelse(df_filtered_resdim6_scenario2$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
table_resdim6_scenario2 <- table(df_filtered_resdim6_scenario2$RESDIM6, df_filtered_resdim6_scenario2$Education_Group)
rownames(table_resdim6_scenario2) <- c("Strongly Disagree", "Neither Agree Nor Disagree")
chi_result_resdim6_scenario2 <- chisq.test(table_resdim6_scenario2)
odds_ratio_resdim6_scenario2 <- oddsratio(table_resdim6_scenario2, conf.level = 0.95)$measure
print(knitr::kable(table_resdim6_scenario2, caption = "Contingency Table: Education Level vs. Perception of Risk of Antibiotic-Resistant Infection (Strongly Disagree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim6_scenario2)
print(odds_ratio_resdim6_scenario2)

# Scenario 3: Strongly Agree + Neither Agree Nor Disagree vs. Strongly Disagree
df_filtered_resdim6_scenario3 <- df[df$RESDIM6 %in% c(1, 2, 3) & df$NIVSCOL %in% c(1, 2, 3, 4, 5, 6, 7, 8), ]
df_filtered_resdim6_scenario3$Education_Group <- ifelse(df_filtered_resdim6_scenario3$NIVSCOL %in% c(7, 8), "Higher Education", "Other Education")
df_filtered_resdim6_scenario3$Agree_Neither <- df_filtered_resdim6_scenario3$RESDIM6 %in% c(2, 3)
table_resdim6_scenario3 <- table(df_filtered_resdim6_scenario3$Agree_Neither, df_filtered_resdim6_scenario3$Education_Group)
rownames(table_resdim6_scenario3) <- c("Strongly Disagree", "Strongly Agree + Neither")
chi_result_resdim6_scenario3 <- chisq.test(table_resdim6_scenario3)
odds_ratio_resdim6_scenario3 <- oddsratio(table_resdim6_scenario3, conf.level = 0.95)$measure
print(knitr::kable(table_resdim6_scenario3, caption = "Contingency Table: Education Level vs. Perception of Risk of Antibiotic-Resistant Infection (Strongly Disagree vs. Strongly Agree + Neither Agree Nor Disagree)"))
print(chi_result_resdim6_scenario3)
print(odds_ratio_resdim6_scenario3)

############################################## Comparisons by Field of work/study (Health and science vs other) ##########################################


###CUSIN1 (I wash my hands before cooking (No= 9.4%))

Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
# Load the Database_simplified dataframe
df_filtered <- Database_simplified

# First, create a new variable 'HEALTH_SCIENCE' that is 0 if either PROF11 or PROF12 is 0, and 1 otherwise
df_filtered$HEALTH_SCIENCE <- ifelse(df_filtered$PROF11 == 0 | df_filtered$PROF12 == 0, 0, 1)

# Now, filter the dataframe to keep only the relevant observations
df_filtered <- df_filtered[df_filtered$CUSIN1 %in% c(0, 1) & df_filtered$HEALTH_SCIENCE %in% c(0, 1), ]

# Create the contingency table
table <- table(df_filtered$CUSIN1, df_filtered$HEALTH_SCIENCE)

# Add descriptive labels to rows and columns
rownames(table) <- c("CUSIN1 (Yes)", "CUSIN1 (No)")
colnames(table) <- c("Health & Science", "Other Professions")

# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Health & Science vs. Hand Washing")

# Chi-Square Test
chi_result <- chisq.test(table)

# Print the results of the Chi-Square Test
print(chi_result)

# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])

# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure

# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

---------------------------------------------------------------------------------------------------
  
  ##CUSIN2 (After handling raw food (meat and vegetables), I wash my hands with soap (No= 15.1%))
  
  # Filter DataFrame to include only the relevant observations for CUSIN2 and professions
  df_filtered <- Database_simplified[Database_simplified$CUSIN2 %in% c(0, 1) & 
                                       (Database_simplified$PROF11 %in% c(0, 1) | 
                                          Database_simplified$PROF12 %in% c(0, 1)), ]
# Create a binary variable for Health & Science Professions
df_filtered$HEALTH_SCIENCE <- ifelse(df_filtered$PROF11 == 0 | df_filtered$PROF12 == 0, 0, 1)
# Create the Contingency Table
table <- table(df_filtered$CUSIN2, df_filtered$HEALTH_SCIENCE)
# Rename rows and columns of the table
rownames(table) <- c("CUSIN2 (Yes)", "CUSIN2 (No)")
colnames(table) <- c("Health & Science", "Other Professions")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Health & Science vs. After handling raw food (meat and vegetables), I wash my hands with soap")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN3 (I use the same kitchen utensils for handling raw and ready-to-eat foods (Yes=25.8%))
  
  # Filter DataFrame to include only the relevant observations for CUSIN3 and professions
  df_filtered <- Database_simplified[Database_simplified$CUSIN3 %in% c(0, 1) & 
                                       (Database_simplified$PROF11 %in% c(0, 1) | 
                                          Database_simplified$PROF12 %in% c(0, 1)), ]

# Create a binary variable for Health & Science Professions
df_filtered$HEALTH_SCIENCE <- ifelse(df_filtered$PROF11 == 0 | df_filtered$PROF12 == 0, 0, 1)
# Create the Contingency Table
table <- table(df_filtered$CUSIN3, df_filtered$HEALTH_SCIENCE)
# Rename rows and columns of the table
rownames(table) <- c("CUSIN3 (Yes)", "CUSIN3 (No)")
colnames(table) <- c("Health & Science", "Other Professions")
# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Health & Science vs. I use the same kitchen utensils for handling raw and ready-to-eat foods")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

-------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN4 (I wash kitchen utensils that have been used for raw food before using them to prepare other foods  (No=16.8%))
  
  # Filter DataFrame to include only the relevant observations for CUSIN4 and professions
  df_filtered <- Database_simplified[Database_simplified$CUSIN4 %in% c(0, 1) & 
                                       (Database_simplified$PROF11 %in% c(0, 1) | 
                                          Database_simplified$PROF12 %in% c(0, 1)), ]

# Create a binary variable for Health & Science Professions
df_filtered$HEALTH_SCIENCE <- ifelse(df_filtered$PROF11 == 0 | df_filtered$PROF12 == 0, 0, 1)

# Create the Contingency Table
table <- table(df_filtered$CUSIN4, df_filtered$HEALTH_SCIENCE)

# Rename rows and columns of the table
rownames(table) <- c("CUSIN4 (Yes)", "CUSIN4 (No)")
colnames(table) <- c("Health & Science", "Other Professions")

# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Health & Science vs. Washing Kitchen Utensils Used for Raw Food Before Using Them for Other Foods")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

-------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN5 (I wash fruits and vegetables before eating them (No=20.7%))
  
  # Filter DataFrame to include only the relevant observations for CUSIN5 and professions
  df_filtered <- Database_simplified[Database_simplified$CUSIN5 %in% c(0, 1) & 
                                       (Database_simplified$PROF11 %in% c(0, 1) | 
                                          Database_simplified$PROF12 %in% c(0, 1)), ]

# Create a binary variable for Health & Science Professions
df_filtered$HEALTH_SCIENCE <- ifelse(df_filtered$PROF11 == 0 | df_filtered$PROF12 == 0, 0, 1)

# Create the Contingency Table
table <- table(df_filtered$CUSIN5, df_filtered$HEALTH_SCIENCE)

# Rename rows and columns of the table
rownames(table) <- c("CUSIN5 (Yes)", "CUSIN5 (No)")
colnames(table) <- c("Health & Science", "Other Professions")

# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Health & Science vs. Washing Fruits and Vegetables Before Eating Them")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

-------------------------------------------------------------------------------------------------------------------
  
  ##CUSIN6 (I wash my hands before eating (No=21.5))
  
  # Filter DataFrame to include only the relevant observations for CUSIN6 and professions
  df_filtered <- Database_simplified[Database_simplified$CUSIN6 %in% c(0, 1) & 
                                       (Database_simplified$PROF11 %in% c(0, 1) | 
                                          Database_simplified$PROF12 %in% c(0, 1)), ]

# Create a binary variable for Health & Science Professions
df_filtered$HEALTH_SCIENCE <- ifelse(df_filtered$PROF11 == 0 | df_filtered$PROF12 == 0, 0, 1)

# Create the Contingency Table
table <- table(df_filtered$CUSIN6, df_filtered$HEALTH_SCIENCE)

# Rename rows and columns of the table
rownames(table) <- c("CUSIN6 (Yes)", "CUSIN6 (No)")
colnames(table) <- c("Health & Science", "Other Professions")

# Print the contingency table using knitr for a formatted output
kable(table, caption = "Contingency Table: Health & Science vs. Washing Hands Before Eating")
# Chi-Square Test
chi_result <- chisq.test(table)
# Print the results of the Chi-Square Test
print(chi_result)
# Calculating the odds ratio for a 2x2 table
odds_ratio <- (table[1, 1] * table[2, 2]) / (table[1, 2] * table[2, 1])
# Calculating the confidence interval
confidence_interval <- oddsratio(table, conf.level = 0.95)$measure
# Printing the odds ratio and confidence interval
print(odds_ratio)
print(confidence_interval)

---------------------------------------------------------------------------------------------------------------------
  
  ##PRESCATB1 When you get a prescription for antibiotics, do you follow the recommended 
  ##length of treatment and daily dosage? (No=4.2%) (Sometimes=9.6%) (No+Sometimes=13.8%)
  
  # Read the database
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
df <- Database_simplified

############### 1st scenario= No
# Filter DataFrame to include only the relevant observations for PRESCATB1 and professions
df_filtered_prescatb1 <- df[df$PRESCATB1 %in% c(0, 1) & (df$PROF11 %in% c(0, 1) | df$PROF12 %in% c(0, 1)), ]
# Create a binary variable for Health & Science Professions
df_filtered_prescatb1$HEALTH_SCIENCE <- ifelse(df_filtered_prescatb1$PROF11 == 0 | df_filtered_prescatb1$PROF12 == 0, 0, 1)
# Create the Contingency Table
table_prescatb1 <- table(df_filtered_prescatb1$PRESCATB1, df_filtered_prescatb1$HEALTH_SCIENCE)
# Add descriptive labels to the rows and columns
rownames(table_prescatb1) <- c("Yes", "No")
colnames(table_prescatb1) <- c("Health & Science", "Other Professions")
# Perform the Chi-Squared test
chi_result_prescatb1 <- chisq.test(table_prescatb1)
# Calculate the odds ratio and confidence interval
odds_ratio_prescatb1 <- oddsratio(table_prescatb1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_prescatb1, caption = "Contingency Table: Profession vs. Following Prescription for Antibiotics"))
# Print the results of the Chi-Squared test
print(chi_result_prescatb1)
# Print the odds ratio and confidence interval
print(odds_ratio_prescatb1)

################## 2nd scenario= Sometimes
# Filter DataFrame to include only the relevant observations for PRESCATB1 and professions
df_filtered_prescatb1_sometimes <- df[df$PRESCATB1 %in% c(0, 3) & 
                                        (df$PROF11 %in% c(0, 1) | df$PROF12 %in% c(0, 1)), ]
# Create a binary variable for Health & Science Professions
df_filtered_prescatb1_sometimes$HEALTH_SCIENCE <- ifelse(df_filtered_prescatb1_sometimes$PROF11 == 0 | df_filtered_prescatb1_sometimes$PROF12 == 0, 0, 1)
# Create the Contingency Table
table_prescatb1_sometimes <- table(df_filtered_prescatb1_sometimes$PRESCATB1, df_filtered_prescatb1_sometimes$HEALTH_SCIENCE)
# Add descriptive labels to the rows and columns
rownames(table_prescatb1_sometimes) <- c("Yes", "Sometimes")
colnames(table_prescatb1_sometimes) <- c("Health & Science", "Other Professions")# Perform the Chi-Squared test
chi_result_prescatb1_sometimes <- chisq.test(table_prescatb1_sometimes)
# Calculate the odds ratio and confidence interval
odds_ratio_prescatb1_sometimes <- oddsratio(table_prescatb1_sometimes, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_prescatb1_sometimes, caption = "Contingency Table: Profession vs. Following Prescription for Antibiotics Sometimes"))
# Print the results of the Chi-Squared test
print(chi_result_prescatb1_sometimes)
# Print the odds ratio and confidence interval
print(odds_ratio_prescatb1_sometimes)

################## 3rd scenario= No+Sometimes
# Filter DataFrame to include only the relevant observations for PRESCATB1 and professions
df_filtered_prescatb1_combined <- df[df$PRESCATB1 %in% c(0, 1, 3) & 
                                       (df$PROF11 %in% c(0, 1) | df$PROF12 %in% c(0, 1)), ]
# Create a binary variable for Health & Science Professions
df_filtered_prescatb1_combined$HEALTH_SCIENCE <- ifelse(df_filtered_prescatb1_combined$PROF11 == 0 | df_filtered_prescatb1_combined$PROF12 == 0, 0, 1)
df_filtered_prescatb1_combined$No_Sometimes <- df_filtered_prescatb1_combined$PRESCATB1 %in% c(1, 3)
# Create the Contingency Table
table_prescatb1_combined <- table(df_filtered_prescatb1_combined$No_Sometimes, df_filtered_prescatb1_combined$HEALTH_SCIENCE)
# Adjust the table to have 'Yes' and 'No+Sometimes' as row names
rownames(table_prescatb1_combined) <- c("Yes", "No_Sometimes")
colnames(table_prescatb1_combined) <- c("Health & Science", "Other Professions")
# Perform the Chi-Squared test
chi_result_prescatb1_combined <- chisq.test(table_prescatb1_combined)
# Calculate the odds ratio and confidence interval
odds_ratio_prescatb1_combined <- oddsratio(table_prescatb1_combined, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_prescatb1_combined, caption = "Contingency Table: Profession vs. Following Prescription for Antibiotics (Yes vs. No+Sometimes)"))
# Print the results of the Chi-Squared test
print(chi_result_prescatb1_combined)
# Print the odds ratio and confidence interval
print(odds_ratio_prescatb1_combined)


---------------------------------------------------------------------------------------------------------------------
  
  ##ARRETATB Do you stop taking antibiotics when symptoms start to disappear?
  ##(Always=7.3%) (Sometimes=20.4%) (Always+Sometimes=27.7%)
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)
df <- Database_simplified
############### 1st scenario= Always
# Filter DataFrame to include only the relevant observations for ARRETATB and professions
df_filtered_arretatb <- df[df$ARRETATB %in% c(0, 1) & 
                             (df$PROF11 %in% c(0, 1) | df$PROF12 %in% c(0, 1)), ]
# Create a binary variable for Health & Science Professions
df_filtered_arretatb$HEALTH_SCIENCE <- ifelse(df_filtered_arretatb$PROF11 == 0 | df_filtered_arretatb$PROF12 == 0, 0, 1)
# Create the Contingency Table
table_arretatb <- table(df_filtered_arretatb$ARRETATB, df_filtered_arretatb$HEALTH_SCIENCE)
# Add descriptive labels to the rows and columns
rownames(table_arretatb) <- c("Always", "Never")
colnames(table_arretatb) <- c("Health & Science", "Other Professions")
# Perform the Chi-Squared test
chi_result_arretatb <- chisq.test(table_arretatb)
# Calculate the odds ratio and confidence interval
odds_ratio_arretatb <- oddsratio(table_arretatb, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_arretatb, caption = "Contingency Table: Profession vs. Stopping Antibiotics Always vs. Never"))
# Print the results of the Chi-Squared test
print(chi_result_arretatb)
# Print the odds ratio and confidence interval
print(odds_ratio_arretatb)

################# 2nd scenario: Sometimes
# Filter DataFrame to include only the relevant observations for ARRETATB and professions
df_filtered_arretatb_sometimes <- df[df$ARRETATB %in% c(1, 2) & 
                                       (df$PROF11 %in% c(0, 1) | df$PROF12 %in% c(0, 1)), ]
# Create a binary variable for Health & Science Professions
df_filtered_arretatb_sometimes$HEALTH_SCIENCE <- ifelse(df_filtered_arretatb_sometimes$PROF11 == 0 | df_filtered_arretatb_sometimes$PROF12 == 0, 0, 1)
# Create the Contingency Table
table_arretatb_sometimes <- table(df_filtered_arretatb_sometimes$ARRETATB == 2, df_filtered_arretatb_sometimes$HEALTH_SCIENCE)
# Add descriptive labels to the rows and columns
rownames(table_arretatb_sometimes) <- c("Never", "Sometimes")
colnames(table_arretatb_sometimes) <- c("Health & Science", "Other Professions")
# Perform the Chi-Squared test
chi_result_arretatb_sometimes <- chisq.test(table_arretatb_sometimes)
# Calculate the odds ratio and confidence interval
odds_ratio_arretatb_sometimes <- oddsratio(table_arretatb_sometimes, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_arretatb_sometimes, caption = "Contingency Table: Profession vs. Stopping Antibiotics Sometimes vs. Never"))
# Print the results of the Chi-Squared test
print(chi_result_arretatb_sometimes)
# Print the odds ratio and confidence interval
print(odds_ratio_arretatb_sometimes)

############### #3rd scenario= Sometimes+Always
# Filter DataFrame to include only the relevant observations for ARRETATB and professions
df_filtered_arretatb_combined <- df[df$ARRETATB %in% c(0, 1, 2) & 
                                      (df$PROF11 %in% c(0, 1) | df$PROF12 %in% c(0, 1)), ]
# Create a binary variable for Health & Science Professions
df_filtered_arretatb_combined$HEALTH_SCIENCE <- ifelse(df_filtered_arretatb_combined$PROF11 == 0 | df_filtered_arretatb_combined$PROF12 == 0, 0, 1)
# Create the Contingency Table
table_arretatb_combined <- table(df_filtered_arretatb_combined$ARRETATB %in% c(0, 2), df_filtered_arretatb_combined$HEALTH_SCIENCE)
# Add descriptive labels to the rows and columns
rownames(table_arretatb_combined) <- c("Never", "Sometimes_Always")
colnames(table_arretatb_combined) <- c("Health & Science", "Other Professions")
# Perform the Chi-Squared test
chi_result_arretatb_combined <- chisq.test(table_arretatb_combined)
# Calculate the odds ratio and confidence interval
odds_ratio_arretatb_combined <- oddsratio(table_arretatb_combined, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_arretatb_combined, caption = "Contingency Table: Profession vs. Stopping Antibiotics (Sometimes+Always vs. Never)"))
# Print the results of the Chi-Squared test
print(chi_result_arretatb_combined)
# Print the odds ratio and confidence interval
print(odds_ratio_arretatb_combined)

---------------------------------------------------------------------------------------------------------------------
  
  ##ATBORAL1 Have you ever taken an oral antibiotic treatment (by mouth) without a medical prescription? (Yes=12.3%)
  df_filtered_atboral <- df[df$ATBORAL1 %in% c(0, 1) & 
                              (df$PROF11 %in% c(0, 1) | df$PROF12 %in% c(0, 1)), ]
# Create a binary variable for Health & Science Professions
df_filtered_atboral$HEALTH_SCIENCE <- ifelse(df_filtered_atboral$PROF11 == 0 | df_filtered_atboral$PROF12 == 0, "Health and Science", "Other Professions")
# Create the Contingency Table
table_atboral <- table(df_filtered_atboral$ATBORAL1, df_filtered_atboral$HEALTH_SCIENCE)
# Add descriptive labels to the rows and columns
rownames(table_atboral) <- c("Yes", "No")
# Perform the Chi-Squared test
chi_result_atboral <- chisq.test(table_atboral)
# Calculate the odds ratio and confidence interval
odds_ratio_atboral <- oddsratio(table_atboral, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atboral, caption = "Contingency Table: Profession vs. Taking Oral Antibiotics Without Prescription (Yes vs. No)"))
# Print the results of the Chi-Squared test
print(chi_result_atboral)
# Print the odds ratio and confidence interval
print(odds_ratio_atboral)


--------------------------------------------------------------------------------------------------------
  
  ### ATBANI1 I can exchange resistant bacteria with my pet (False=23.2%)
  # Filter DataFrame for the relevant variables: ATBANI1 and PROF11/PROF12
  df_filtered_atbani1 <- df[df$ATBANI1 %in% c(0, 1), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_atbani1$HEALTH_SCIENCE <- ifelse(df_filtered_atbani1$PROF11 == 0 | df_filtered_atbani1$PROF12 == 0, "Health and Science", "Other Professions")
# Create the contingency table
table_atbani1 <- table(df_filtered_atbani1$ATBANI1, df_filtered_atbani1$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_atbani1) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_atbani1 <- chisq.test(table_atbani1)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani1 <- oddsratio(table_atbani1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani1, caption = "Contingency Table: Health and Science vs. Other Professions vs. Exchanging Resistant Bacteria with Pets (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani1)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani1)

---------------------------------------------------------------------------------------------------------------------
  
  ### ATBANI2=The use of antibiotics in livestock and crops can increase the 
  #presence of resistant bacteria in the environment (False=14.7%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Filter DataFrame for the relevant variable: ATBANI2
df_filtered_atbani2 <- df[df$ATBANI2 %in% c(0, 1), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_atbani2$HEALTH_SCIENCE <- ifelse(df_filtered_atbani2$PROF11 == 0 | df_filtered_atbani2$PROF12 == 0, "Health and Science", "Other Professions")
# Create the contingency table
table_atbani2 <- table(df_filtered_atbani2$ATBANI2, df_filtered_atbani2$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_atbani2) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_atbani2 <- chisq.test(table_atbani2)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani2 <- oddsratio(table_atbani2, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani2, caption = "Contingency Table: Health and Science vs. Other Professions vs. Antibiotics in Livestock and Crops Affecting Environment (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani2)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani2)


--------------------------------------------------------------------------------------------------------------------
  
  ##### ATBANI3	The use of antibiotics in livestock and crops can affect me directly
  ##(I can get resistant bacteria in my body) (False=26.3%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
df <- Database_simplified  
# Filter DataFrame for the relevant variable: ATBANI3
df_filtered_atbani3 <- df[df$ATBANI3 %in% c(0, 1), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_atbani3$HEALTH_SCIENCE <- ifelse(df_filtered_atbani3$PROF11 == 0 | df_filtered_atbani3$PROF12 == 0, "Health and Science", "Other Professions")
# Create the contingency table
table_atbani3 <- table(df_filtered_atbani3$ATBANI3, df_filtered_atbani3$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_atbani3) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_atbani3 <- chisq.test(table_atbani3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani3 <- oddsratio(table_atbani3, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani3, caption = "Contingency Table: Health and Science vs. Other Professions vs. Antibiotics in Livestock and Crops Affecting Humans Directly (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani3)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani3)

-------------------------------------------------------------------------------------------------------------------
  ##### ATBANI4	Resistant bacteria are only found in hospitals (True=10.8%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
df <- Database_simplified  
# Filter DataFrame for the relevant variable: ATBANI4
df_filtered_atbani4 <- df[df$ATBANI4 %in% c(0, 1), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_atbani4$HEALTH_SCIENCE <- ifelse(df_filtered_atbani4$PROF11 == 0 | df_filtered_atbani4$PROF12 == 0, "Health and Science", "Other Professions")
# Create the contingency table
table_atbani4 <- table(df_filtered_atbani4$ATBANI4, df_filtered_atbani4$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_atbani4) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_atbani4 <- chisq.test(table_atbani4)
# Calculate the odds ratio and confidence interval
odds_ratio_atbani4 <- oddsratio(table_atbani4, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbani4, caption = "Contingency Table: Health and Science vs. Other Professions vs. Resistant Bacteria Found Only in Hospitals (True vs. False)"))
# Print the results of the Chi-Squared test
print(chi_result_atbani4)
# Print the odds ratio and confidence interval
print(odds_ratio_atbani4)

----------------------------------------------------------------------------------------------------------------------
  
  #####RESATB1	Antibiotic resistance occurs when your body becomes resistant to antibiotics and they
  ##no longer work as well (True=58.3%)
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
df <- Database_simplified  
# Filter DataFrame for the relevant variable: RESATB1
df_filtered_resatb1 <- df[df$RESATB1 %in% c(0, 1), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_resatb1$HEALTH_SCIENCE <- ifelse(df_filtered_resatb1$PROF11 == 0 | df_filtered_resatb1$PROF12 == 0, "Health and Science", "Other Professions")
# Create the contingency table
table_resatb1 <- table(df_filtered_resatb1$RESATB1, df_filtered_resatb1$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_resatb1) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_resatb1 <- chisq.test(table_resatb1)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb1 <- oddsratio(table_resatb1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb1, caption = "Contingency Table: Health and Science vs. Other Professions vs. Understanding of Antibiotic Resistance (RESATB1: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb1)
print(odds_ratio_resatb1)

-------------------------------------------------------------------------------------------------------------------
  
  #####RESATB2	Many infections are becoming increasingly resistant to antibiotic treatment  (False=12.5%)
  
  # Load the database
  df <- Database_simplified
# Filter DataFrame for the relevant variable: RESATB2
df_filtered_resatb2 <- df[df$RESATB2 %in% c(0, 1), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_resatb2$HEALTH_SCIENCE <- ifelse(df_filtered_resatb2$PROF11 == 0 | df_filtered_resatb2$PROF12 == 0, "Health and Science", "Other Professions")
# Create the contingency table
table_resatb2 <- table(df_filtered_resatb2$RESATB2, df_filtered_resatb2$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_resatb2) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_resatb2 <- chisq.test(table_resatb2)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb2 <- oddsratio(table_resatb2, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb2, caption = "Contingency Table: Health and Science vs. Other Professions vs. Perception of Increasing Infection Resistance (RESATB2: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb2)
print(odds_ratio_resatb2)

---------------------------------------------------------------------------------------------------------------------
  #####RESATB3	If bacteria are resistant to antibiotics, it can be very difficult or impossible to treat the infections they cause (False=16.7%)
  
  # Load the database
  df <- Database_simplified
# Filter DataFrame for the relevant variable: RESATB3
df_filtered_resatb3 <- df[df$RESATB3 %in% c(0, 1), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_resatb3$HEALTH_SCIENCE <- ifelse(df_filtered_resatb3$PROF11 == 0 | df_filtered_resatb3$PROF12 == 0, "Health and Science", "Other Professions")
# Create the contingency table
table_resatb3 <- table(df_filtered_resatb3$RESATB3, df_filtered_resatb3$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_resatb3) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_resatb3 <- chisq.test(table_resatb3)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb3 <- oddsratio(table_resatb3, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb3, caption = "Contingency Table: Health and Science vs. Other Professions vs. Perception of Difficulty Treating Infections (RESATB3: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb3)
print(odds_ratio_resatb3)
----------------------------------------------------------------------------------------------------------------------
  #####RESATB4	Antibiotic resistance is an issue that could affect me or my family (False=11.8%)
  
  # Load the database
  df <- Database_simplified
# Filter DataFrame for the relevant variable: RESATB4
df_filtered_resatb4 <- df[df$RESATB4 %in% c(0, 1), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_resatb4$HEALTH_SCIENCE <- ifelse(df_filtered_resatb4$PROF11 == 0 | df_filtered_resatb4$PROF12 == 0, "Health and Science", "Other Professions")
# Create the contingency table
table_resatb4 <- table(df_filtered_resatb4$RESATB4, df_filtered_resatb4$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_resatb4) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_resatb4 <- chisq.test(table_resatb4)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb4 <- oddsratio(table_resatb4, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb4, caption = "Contingency Table: Health and Science vs. Other Professions vs. Perception of Antibiotic Resistance Affecting One's Family (RESATB4: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb4)
print(odds_ratio_resatb4)

---------------------------------------------------------------------------------------------------------------------
  #####RESATB5	Antibiotic resistance is an issue in other countries but not here (True=9.9%)
  
  # Load the database
  df <- Database_simplified
# Filter DataFrame for the relevant variable: RESATB5
df_filtered_resatb5 <- df[df$RESATB5 %in% c(0, 1), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_resatb5$HEALTH_SCIENCE <- ifelse(df_filtered_resatb5$PROF11 == 0 | df_filtered_resatb5$PROF12 == 0, "Health and Science", "Other Professions")
# Create the contingency table
table_resatb5 <- table(df_filtered_resatb5$RESATB5, df_filtered_resatb5$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_resatb5) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_resatb5 <- chisq.test(table_resatb5)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb5 <- oddsratio(table_resatb5, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb5, caption = "Contingency Table: Health and Science vs. Other Professions vs. Perception of Antibiotic Resistance as an Issue Only in Other Countries (RESATB5: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb5)
print(odds_ratio_resatb5)
---------------------------------------------------------------------------------------------------------------------  
  
  #####RESATB6	Antibiotic resistance is only a problem for people who take antibiotics regularly (True=17.5%)
  
  # Load the database
  df <- Database_simplified
# Filter DataFrame for the relevant variable: RESATB6
df_filtered_resatb6 <- df[df$RESATB6 %in% c(0, 1), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_resatb6$HEALTH_SCIENCE <- ifelse(df_filtered_resatb6$PROF11 == 0 | df_filtered_resatb6$PROF12 == 0, "Health and Science", "Other Professions")
# Create the contingency table
table_resatb6 <- table(df_filtered_resatb6$RESATB6, df_filtered_resatb6$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_resatb6) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_resatb6 <- chisq.test(table_resatb6)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb6 <- oddsratio(table_resatb6, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb6, caption = "Contingency Table: Health and Science vs. Other Professions vs. Perception of Antibiotic Resistance as a Problem Only for Regular Antibiotic Users (RESATB6: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb6)
print(odds_ratio_resatb6)

--------------------------------------------------------------------------------------------------------------------- 
  #####RESATB7	Bacteria that are resistant to antibiotics can be spread from person to person (False=20.2%)
  
  # Load the database
  df <- Database_simplified
# Filter DataFrame for the relevant variable: RESATB7
df_filtered_resatb7 <- df[df$RESATB7 %in% c(0, 1), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_resatb7$HEALTH_SCIENCE <- ifelse(df_filtered_resatb7$PROF11 == 0 | df_filtered_resatb7$PROF12 == 0, "Health and Science", "Other Professions")
# Create the contingency table
table_resatb7 <- table(df_filtered_resatb7$RESATB7, df_filtered_resatb7$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_resatb7) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_resatb7 <- chisq.test(table_resatb7)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb7 <- oddsratio(table_resatb7, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb7, caption = "Contingency Table: Health and Science vs. Other Professions vs. Perception of Bacteria Transmission Person to Person (RESATB7: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb7)
print(odds_ratio_resatb7)

--------------------------------------------------------------------------------------------------------------------
  #####RESATB8	Antibiotic-resistant infections could make medical procedures like surgery, organ transplants,
  ##and cancer treatment much more dangerous (False=12.0%)
  
  # Load the database
  df <- Database_simplified
# Filter DataFrame for the relevant variable: RESATB8
df_filtered_resatb8 <- df[df$RESATB8 %in% c(0, 1), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_resatb8$HEALTH_SCIENCE <- ifelse(df_filtered_resatb8$PROF11 == 0 | df_filtered_resatb8$PROF12 == 0, "Health and Science", "Other Professions")
# Create the contingency table
table_resatb8 <- table(df_filtered_resatb8$RESATB8, df_filtered_resatb8$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_resatb8) <- c("True", "False")
# Perform the Chi-Squared test
chi_result_resatb8 <- chisq.test(table_resatb8)
# Calculate the odds ratio and confidence interval
odds_ratio_resatb8 <- oddsratio(table_resatb8, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_resatb8, caption = "Contingency Table: Health and Science vs. Other Professions vs. Perception of Antibiotic-Resistant Infections and Medical Procedures (RESATB8: True vs. False)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_resatb8)
print(odds_ratio_resatb8)

--------------------------------------------------------------------------------------------------------------------
  
  # Load dataframe
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
df <- Database_simplified
# Filter DataFrame for the relevant variable: ATBRGL1
df_filtered_atbrgl1_scenario1 <- df[df$ATBRGL1 %in% c(1, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_atbrgl1_scenario1$HEALTH_SCIENCE <- ifelse(df_filtered_atbrgl1_scenario1$PROF11 == 0 | df_filtered_atbrgl1_scenario1$PROF12 == 0, "Health and Science", "Other Professions")
# Create the contingency table
table_atbrgl1_scenario1 <- table(df_filtered_atbrgl1_scenario1$ATBRGL1, df_filtered_atbrgl1_scenario1$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_atbrgl1_scenario1) <- c("Strongly Disagree", "Strongly Agree")
# Perform the Chi-Squared test
chi_result_atbrgl1_scenario1 <- chisq.test(table_atbrgl1_scenario1)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl1_scenario1 <- oddsratio(table_atbrgl1_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl1_scenario1, caption = "Contingency Table: Health and Science vs. Other Professions vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_atbrgl1_scenario1)
print(odds_ratio_atbrgl1_scenario1)

############################# 2nd scenario Farmers should give fewer antibiotics to
##food-producing animals (Neither agree nor desagree=22.6%) vs. Strongly Agree
# Load dataframe
df <- Database_simplified
# Filter DataFrame for the relevant variable: ATBRGL1
df_filtered_atbrgl1_scenario2 <- df[df$ATBRGL1 %in% c(2, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_atbrgl1_scenario2$HEALTH_SCIENCE <- ifelse(df_filtered_atbrgl1_scenario2$PROF11 == 0 | df_filtered_atbrgl1_scenario2$PROF12 == 0, "Health and Science", "Other Professions")
# Create the contingency table
table_atbrgl1_scenario2 <- table(df_filtered_atbrgl1_scenario2$ATBRGL1, df_filtered_atbrgl1_scenario2$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_atbrgl1_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
# Perform the Chi-Squared test
chi_result_atbrgl1_scenario2 <- chisq.test(table_atbrgl1_scenario2)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl1_scenario2 <- oddsratio(table_atbrgl1_scenario2, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl1_scenario2, caption = "Contingency Table: Health and Science vs. Other Professions vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Neither Agree Nor Disagree)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_atbrgl1_scenario2)
print(odds_ratio_atbrgl1_scenario2)

############################# 3rd scenario (Strongly desagree + Neither agree nor desagree=31.28%) vs. Strongly Agree
# Load dataframe
df <- Database_simplified
# Filter DataFrame for the relevant variable: ATBRGL1
df_filtered_atbrgl1_scenario3 <- df[df$ATBRGL1 %in% c(1, 2, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_atbrgl1_scenario3$HEALTH_SCIENCE <- ifelse(df_filtered_atbrgl1_scenario3$PROF11 == 0 | df_filtered_atbrgl1_scenario3$PROF12 == 0, "Health and Science", "Other Professions")
# Categorize responses into Strongly Agree vs. Strongly Disagree + Neither
df_filtered_atbrgl1_scenario3$Disagree_Neither <- df_filtered_atbrgl1_scenario3$ATBRGL1 %in% c(1, 2)
# Create the contingency table
table_atbrgl1_scenario3 <- table(df_filtered_atbrgl1_scenario3$Disagree_Neither, df_filtered_atbrgl1_scenario3$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_atbrgl1_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
# Perform the Chi-Squared test
chi_result_atbrgl1_scenario3 <- chisq.test(table_atbrgl1_scenario3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl1_scenario3 <- oddsratio(table_atbrgl1_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl1_scenario3, caption = "Contingency Table: Health and Science vs. Other Professions vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree + Neither)"))
# Print the results of the Chi-Squared test and odds ratio
print(chi_result_atbrgl1_scenario3)
print(odds_ratio_atbrgl1_scenario3)

--------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL2	People should not keep antibiotics and use them later for other illnesses  
  
  ############################# 1st scenario Strongly desagree vs. Strongly Agree
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the database
df <- Database_simplified
## Scenario 1: Strongly Disagree vs. Strongly Agree
df_filtered_atbrgl2_scenario1 <- df[df$ATBRGL2 %in% c(1, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_atbrgl2_scenario1$HEALTH_SCIENCE <- ifelse(df_filtered_atbrgl2_scenario1$PROF11 == 0 | df_filtered_atbrgl2_scenario1$PROF12 == 0, "Health and Science", "Other Professions")
# Create the contingency table
table_atbrgl2_scenario1 <- table(df_filtered_atbrgl2_scenario1$ATBRGL2, df_filtered_atbrgl2_scenario1$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_atbrgl2_scenario1) <- c("Strongly Disagree", "Strongly Agree")
# Perform Chi-Squared test
chi_result_atbrgl2_scenario1 <- chisq.test(table_atbrgl2_scenario1)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl2_scenario1 <- oddsratio(table_atbrgl2_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl2_scenario1, caption = "Contingency Table: Health and Science vs. Other Professions vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl2_scenario1)
print(odds_ratio_atbrgl2_scenario1)

############################# 2nd scenario Neither agree nor desagree vs. Strongly Agree
# Filter for 'Strongly Agree' (3) and 'Neither Agree Nor Disagree' (2) responses for ATBRGL2
df_filtered_atbrgl2_scenario2 <- df[df$ATBRGL2 %in% c(2, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_atbrgl2_scenario2$HEALTH_SCIENCE <- ifelse(df_filtered_atbrgl2_scenario2$PROF11 == 0 | df_filtered_atbrgl2_scenario2$PROF12 == 0, "Health and Science", "Other Professions")
# Create the contingency table
table_atbrgl2_scenario2 <- table(df_filtered_atbrgl2_scenario2$ATBRGL2, df_filtered_atbrgl2_scenario2$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_atbrgl2_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
# Perform Chi-Squared test
chi_result_atbrgl2_scenario2 <- chisq.test(table_atbrgl2_scenario2)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl2_scenario2 <- oddsratio(table_atbrgl2_scenario2, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl2_scenario2, caption = "Contingency Table: Health and Science vs. Other Professions vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl2_scenario2)
print(odds_ratio_atbrgl2_scenario2)


############################# 3rd scenario Neither agree nor desagree + Stringly Disagree vs. Strongly Agree
df_filtered_atbrgl2_scenario3 <- df[df$ATBRGL2 %in% c(1, 2, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_atbrgl2_scenario3$HEALTH_SCIENCE <- ifelse(df_filtered_atbrgl2_scenario3$PROF11 == 0 | df_filtered_atbrgl2_scenario3$PROF12 == 0, "Health and Science", "Other Professions")
# Categorize responses into Strongly Agree vs. Strongly Disagree + Neither
df_filtered_atbrgl2_scenario3$Disagree_Neither <- df_filtered_atbrgl2_scenario3$ATBRGL2 %in% c(1, 2)
# Create the contingency table
table_atbrgl2_scenario3 <- table(df_filtered_atbrgl2_scenario3$Disagree_Neither, df_filtered_atbrgl2_scenario3$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_atbrgl2_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
# Perform the Chi-Squared test
chi_result_atbrgl2_scenario3 <- chisq.test(table_atbrgl2_scenario3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl2_scenario3 <- oddsratio(table_atbrgl2_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl2_scenario3, caption = "Contingency Table: Health and Science vs. Other Professions vs. Opinion on Antibiotics in Farming (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl2_scenario3)
print(odds_ratio_atbrgl2_scenario3)

--------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL3 Parents should make sure all of their children’s vaccinations are up-to-date 
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
View(Database_simplified)

####1st scenario
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl3_scenario1 <- df[df$ATBRGL3 %in% c(1, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_atbrgl3_scenario1$HEALTH_SCIENCE <- ifelse(df_filtered_atbrgl3_scenario1$PROF11 == 0 | df_filtered_atbrgl3_scenario1$PROF12 == 0, "Health and Science", "Other Professions")
# Create the contingency table
table_atbrgl3_scenario1 <- table(df_filtered_atbrgl3_scenario1$ATBRGL3, df_filtered_atbrgl3_scenario1$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_atbrgl3_scenario1) <- c("Strongly Disagree", "Strongly Agree")
# Perform Chi-Squared test
chi_result_atbrgl3_scenario1 <- chisq.test(table_atbrgl3_scenario1)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl3_scenario1 <- oddsratio(table_atbrgl3_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl3_scenario1, caption = "Contingency Table: Health and Science vs. Other Professions vs. Opinion on Children's Vaccinations (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl3_scenario1)
print(odds_ratio_atbrgl3_scenario1)

### 2nd Scenario
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl3_scenario2 <- df[df$ATBRGL3 %in% c(2, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_atbrgl3_scenario2$HEALTH_SCIENCE <- ifelse(df_filtered_atbrgl3_scenario2$PROF11 == 0 | df_filtered_atbrgl3_scenario2$PROF12 == 0, "Health and Science", "Other Professions")
# Create the contingency table
table_atbrgl3_scenario2 <- table(df_filtered_atbrgl3_scenario2$ATBRGL3, df_filtered_atbrgl3_scenario2$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_atbrgl3_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
# Perform Chi-Squared test
chi_result_atbrgl3_scenario2 <- chisq.test(table_atbrgl3_scenario2)
# Calculate odds ratio and confidence interval
odds_ratio_atbrgl3_scenario2 <- oddsratio(table_atbrgl3_scenario2, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl3_scenario2, caption = "Contingency Table: Health and Science vs. Other Professions vs. Opinion on Children's Vaccinations (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl3_scenario2)
print(odds_ratio_atbrgl3_scenario2)

## 3rd scenario
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl3_scenario3 <- df[df$ATBRGL3 %in% c(1, 2, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_atbrgl3_scenario3$HEALTH_SCIENCE <- ifelse(df_filtered_atbrgl3_scenario3$PROF11 == 0 | df_filtered_atbrgl3_scenario3$PROF12 == 0, "Health and Science", "Other Professions")
# Categorize responses into Strongly Agree vs. Strongly Disagree + Neither
df_filtered_atbrgl3_scenario3$Disagree_Neither <- df_filtered_atbrgl3_scenario3$ATBRGL3 %in% c(1, 2)
# Create the contingency table
table_atbrgl3_scenario3 <- table(df_filtered_atbrgl3_scenario3$Disagree_Neither, df_filtered_atbrgl3_scenario3$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_atbrgl3_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
# Perform the Chi-Squared test
chi_result_atbrgl3_scenario3 <- chisq.test(table_atbrgl3_scenario3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl3_scenario3 <- oddsratio(table_atbrgl3_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(kable(table_atbrgl3_scenario3, caption = "Contingency Table: Health and Science vs. Other Professions vs. Opinion on Children's Vaccinations (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl3_scenario3)
print(odds_ratio_atbrgl3_scenario3)

---------------------------------------------------------------------------------------------------------------------
  
  # ATBRGL4 People should wash their hands regularly
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

## Scenario 1: Strongly Disagree vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl4_scenario1 <- df[df$ATBRGL4 %in% c(1, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_atbrgl4_scenario1$HEALTH_SCIENCE <- ifelse(df_filtered_atbrgl4_scenario1$PROF11 == 0 | df_filtered_atbrgl4_scenario1$PROF12 == 0, "Health and Science", "Other Professions")
# Create the contingency table
table_atbrgl4_scenario1 <- table(df_filtered_atbrgl4_scenario1$ATBRGL4, df_filtered_atbrgl4_scenario1$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_atbrgl4_scenario1) <- c("Strongly Disagree", "Strongly Agree")
# Perform the Chi-Squared test
chi_result_atbrgl4_scenario1 <- chisq.test(table_atbrgl4_scenario1)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl4_scenario1 <- oddsratio(table_atbrgl4_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl4_scenario1, caption = "Contingency Table: Health and Science vs. Other Professions vs. Hand Washing Importance (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl4_scenario1)
print(odds_ratio_atbrgl4_scenario1)

## Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl4_scenario2 <- df[df$ATBRGL4 %in% c(2, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_atbrgl4_scenario2$HEALTH_SCIENCE <- ifelse(df_filtered_atbrgl4_scenario2$PROF11 == 0 | df_filtered_atbrgl4_scenario2$PROF12 == 0, "Health and Science", "Other Professions")
# Create the contingency table
table_atbrgl4_scenario2 <- table(df_filtered_atbrgl4_scenario2$ATBRGL4, df_filtered_atbrgl4_scenario2$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_atbrgl4_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
# Perform the Chi-Squared test
chi_result_atbrgl4_scenario2 <- chisq.test(table_atbrgl4_scenario2)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl4_scenario2 <- oddsratio(table_atbrgl4_scenario2, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl4_scenario2, caption = "Contingency Table: Health and Science vs. Other Professions vs. Hand Washing Importance (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl4_scenario2)
print(odds_ratio_atbrgl4_scenario2)

## Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl4_scenario3 <- df[df$ATBRGL4 %in% c(1, 2, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_atbrgl4_scenario3$HEALTH_SCIENCE <- ifelse(df_filtered_atbrgl4_scenario3$PROF11 == 0 | df_filtered_atbrgl4_scenario3$PROF12 == 0, "Health and Science", "Other Professions")
# Categorize responses into Strongly Agree vs. Strongly Disagree + Neither
df_filtered_atbrgl4_scenario3$Disagree_Neither <- df_filtered_atbrgl4_scenario3$ATBRGL4 %in% c(1, 2)
# Create the contingency table
table_atbrgl4_scenario3 <- table(df_filtered_atbrgl4_scenario3$Disagree_Neither, df_filtered_atbrgl4_scenario3$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_atbrgl4_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
# Perform the Chi-Squared test
chi_result_atbrgl4_scenario3 <- chisq.test(table_atbrgl4_scenario3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl4_scenario3 <- oddsratio(table_atbrgl4_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl4_scenario3, caption = "Contingency Table: Health and Science vs. Other Professions vs. Hand Washing Importance (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl4_scenario3)
print(odds_ratio_atbrgl4_scenario3)

---------------------------------------------------------------------------------------------------------------------
  
  #ATBRGL5 Doctors should only prescribe antibiotics when they are needed 
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)

# Load the Database_simplified dataframe
df <- Database_simplified

## Scenario 1: Strongly Disagree vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl5_scenario1 <- df[df$ATBRGL5 %in% c(1, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_atbrgl5_scenario1$HEALTH_SCIENCE <- ifelse(df_filtered_atbrgl5_scenario1$PROF11 == 0 | df_filtered_atbrgl5_scenario1$PROF12 == 0, "Health and Science", "Other Professions")
# Create the contingency table
table_atbrgl5_scenario1 <- table(df_filtered_atbrgl5_scenario1$ATBRGL5, df_filtered_atbrgl5_scenario1$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_atbrgl5_scenario1) <- c("Strongly Disagree", "Strongly Agree")
# Perform the Chi-Squared test
chi_result_atbrgl5_scenario1 <- chisq.test(table_atbrgl5_scenario1)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl5_scenario1 <- oddsratio(table_atbrgl5_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl5_scenario1, caption = "Contingency Table: Health and Science vs. Other Professions vs. Antibiotic Prescription Necessity (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl5_scenario1)
print(odds_ratio_atbrgl5_scenario1)

## Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl5_scenario2 <- df[df$ATBRGL5 %in% c(2, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_atbrgl5_scenario2$HEALTH_SCIENCE <- ifelse(df_filtered_atbrgl5_scenario2$PROF11 == 0 | df_filtered_atbrgl5_scenario2$PROF12 == 0, "Health and Science", "Others")
# Create the contingency table
table_atbrgl5_scenario2 <- table(df_filtered_atbrgl5_scenario2$ATBRGL5, df_filtered_atbrgl5_scenario2$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_atbrgl5_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
# Perform the Chi-Squared test
chi_result_atbrgl5_scenario2 <- chisq.test(table_atbrgl5_scenario2)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl5_scenario2 <- oddsratio(table_atbrgl5_scenario2, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl5_scenario2, caption = "Contingency Table: Health and Science vs. Others vs. Antibiotic Prescription Necessity (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl5_scenario2)
print(odds_ratio_atbrgl5_scenario2)

## Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl5_scenario3 <- df[df$ATBRGL5 %in% c(1, 2, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_atbrgl5_scenario3$HEALTH_SCIENCE <- ifelse(df_filtered_atbrgl5_scenario3$PROF11 == 0 | df_filtered_atbrgl5_scenario3$PROF12 == 0, "Health and Science", "Other Education")
# Categorize responses into Strongly Agree vs. Strongly Disagree + Neither
df_filtered_atbrgl5_scenario3$Disagree_Neither <- df_filtered_atbrgl5_scenario3$ATBRGL5 %in% c(1, 2)
# Create the contingency table
table_atbrgl5_scenario3 <- table(df_filtered_atbrgl5_scenario3$Disagree_Neither, df_filtered_atbrgl5_scenario3$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_atbrgl5_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
# Perform the Chi-Squared test
chi_result_atbrgl5_scenario3 <- chisq.test(table_atbrgl5_scenario3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl5_scenario3 <- oddsratio(table_atbrgl5_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl5_scenario3, caption = "Contingency Table: Health and Science vs. Other Education vs. Antibiotic Prescription Necessity (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl5_scenario3)
print(odds_ratio_atbrgl5_scenario3)

----------------------------------------------------------------------------------------------------------------------
  
  ##ATBRGL6= People should only use antibiotics when prescribed by a doctor or nurse
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

## Scenario 1: Strongly Disagree vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl6_scenario1 <- df[df$ATBRGL6 %in% c(1, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_atbrgl6_scenario1$HEALTH_SCIENCE <- ifelse(df_filtered_atbrgl6_scenario1$PROF11 == 0 | df_filtered_atbrgl6_scenario1$PROF12 == 0, "Health and Science", "Other Education")
# Create the contingency table
table_atbrgl6_scenario1 <- table(df_filtered_atbrgl6_scenario1$ATBRGL6, df_filtered_atbrgl6_scenario1$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_atbrgl6_scenario1) <- c("Strongly Disagree", "Strongly Agree")
# Perform the Chi-Squared test
chi_result_atbrgl6_scenario1 <- chisq.test(table_atbrgl6_scenario1)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl6_scenario1 <- oddsratio(table_atbrgl6_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl6_scenario1, caption = "Contingency Table: Health and Science vs. Other Education vs. Antibiotic only when prescribed (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_atbrgl6_scenario1)
print(odds_ratio_atbrgl6_scenario1)

## Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl6_scenario2 <- df[df$ATBRGL6 %in% c(2, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_atbrgl6_scenario2$HEALTH_SCIENCE <- ifelse(df_filtered_atbrgl6_scenario2$PROF11 == 0 | df_filtered_atbrgl6_scenario2$PROF12 == 0, "Health and Science", "Other Education")
# Create the contingency table
table_atbrgl6_scenario2 <- table(df_filtered_atbrgl6_scenario2$ATBRGL6, df_filtered_atbrgl6_scenario2$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_atbrgl6_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
# Perform the Chi-Squared test
chi_result_atbrgl6_scenario2 <- chisq.test(table_atbrgl6_scenario2)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl6_scenario2 <- oddsratio(table_atbrgl6_scenario2, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl6_scenario2, caption = "Contingency Table: Health and Science vs. Other Education vs. Antibiotic only when prescribed (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_atbrgl6_scenario2)
print(odds_ratio_atbrgl6_scenario2)

## Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_atbrgl6_scenario3 <- df[df$ATBRGL6 %in% c(1, 2, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_atbrgl6_scenario3$HEALTH_SCIENCE <- ifelse(df_filtered_atbrgl6_scenario3$PROF11 == 0 | df_filtered_atbrgl6_scenario3$PROF12 == 0, "Health and Science", "Other Education")
# Categorize responses into Strongly Agree vs. Strongly Disagree + Neither
df_filtered_atbrgl6_scenario3$Disagree_Neither <- df_filtered_atbrgl6_scenario3$ATBRGL6 %in% c(1, 2)
# Create the contingency table
table_atbrgl6_scenario3 <- table(df_filtered_atbrgl6_scenario3$Disagree_Neither, df_filtered_atbrgl6_scenario3$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_atbrgl6_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
# Perform the Chi-Squared test
chi_result_atbrgl6_scenario3 <- chisq.test(table_atbrgl6_scenario3)
# Calculate the odds ratio and confidence interval
odds_ratio_atbrgl6_scenario3 <- oddsratio(table_atbrgl6_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table
print(kable(table_atbrgl6_scenario3, caption = "Contingency Table: Health and Science vs. Other Education vs. Antibiotic only when prescribed (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_atbrgl6_scenario3)
print(odds_ratio_atbrgl6_scenario3)

----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM1= Antibiotic resistance is one of the biggest problems the world faces
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_resdim1_scenario1 <- df[df$RESDIM1 %in% c(1, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_resdim1_scenario1$HEALTH_SCIENCE <- ifelse(df_filtered_resdim1_scenario1$PROF11 == 0 | df_filtered_resdim1_scenario1$PROF12 == 0, "Health and Science", "Other Education")
# Create the contingency table
table_resdim1_scenario1 <- table(df_filtered_resdim1_scenario1$RESDIM1, df_filtered_resdim1_scenario1$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_resdim1_scenario1) <- c("Strongly Disagree", "Strongly Agree")
# Perform the Chi-Squared test
chi_result_resdim1_scenario1 <- chisq.test(table_resdim1_scenario1)
# Calculate the odds ratio and confidence interval
odds_ratio_resdim1_scenario1 <- oddsratio(table_resdim1_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(knitr::kable(table_resdim1_scenario1, caption = "Contingency Table: Health and Science vs. Other Education vs. Perception of Antibiotic Resistance as a Global Problem (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_resdim1_scenario1)
print(odds_ratio_resdim1_scenario1)


# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_resdim1_scenario2 <- df[df$RESDIM1 %in% c(2, 3), ]
# Create the HEALTH_SCIENCE variable
df_filtered_resdim1_scenario2$HEALTH_SCIENCE <- ifelse(df_filtered_resdim1_scenario2$PROF11 == 0 | df_filtered_resdim1_scenario2$PROF12 == 0, "Health and Science", "Other Education")
# Create the contingency table
table_resdim1_scenario2 <- table(df_filtered_resdim1_scenario2$RESDIM1, df_filtered_resdim1_scenario2$HEALTH_SCIENCE)
# Add descriptive labels
rownames(table_resdim1_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
# Perform the Chi-Squared test
chi_result_resdim1_scenario2 <- chisq.test(table_resdim1_scenario2)
# Calculate odds ratio and confidence interval
odds_ratio_resdim1_scenario2 <- oddsratio(table_resdim1_scenario2, conf.level = 0.95)$measure
# Print the table and results
print(knitr::kable(table_resdim1_scenario2, caption = "Contingency Table: Health and Science vs. Other Education vs. Perception of Antibiotic Resistance as a Global Problem (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim1_scenario2)
print(odds_ratio_resdim1_scenario2)


# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_resdim1_scenario3 <- df[df$RESDIM1 %in% c(1, 2, 3), ]
# Create the HEALTH_SCIENCE variable
df_filtered_resdim1_scenario3$HEALTH_SCIENCE <- ifelse(df_filtered_resdim1_scenario3$PROF11 == 0 | df_filtered_resdim1_scenario3$PROF12 == 0, "Health and Science", "Other Education")
# Categorize responses
df_filtered_resdim1_scenario3$Disagree_Neither <- df_filtered_resdim1_scenario3$RESDIM1 %in% c(1, 2)
# Create the contingency table
table_resdim1_scenario3 <- table(df_filtered_resdim1_scenario3$Disagree_Neither, df_filtered_resdim1_scenario3$HEALTH_SCIENCE)
# Add descriptive labels
rownames(table_resdim1_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
# Perform the Chi-Squared test
chi_result_resdim1_scenario3 <- chisq.test(table_resdim1_scenario3)
# Calculate odds ratio and confidence interval
odds_ratio_resdim1_scenario3 <- oddsratio(table_resdim1_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(knitr::kable(table_resdim1_scenario3, caption = "Contingency Table: Health and Science vs. Other Education vs. Perception of Antibiotic Resistance as a Global Problem (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_resdim1_scenario3)
print(odds_ratio_resdim1_scenario3)

----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM2= Medical experts will solve the problem of antibiotic resistance before it becomes too serious 
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Load the Database_simplified dataframe
df <- read_excel("C:/Database_simplified.xlsx")

# Scenario 1: Strongly Agree vs. Strongly Disagree
# Load dataframe
df <- Database_simplified
df_filtered_resdim2_scenario1 <- df[df$RESDIM2 %in% c(1, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_resdim2_scenario1$HEALTH_SCIENCE <- ifelse(df_filtered_resdim2_scenario1$PROF11 == 0 | df_filtered_resdim2_scenario1$PROF12 == 0, "Health and Science", "Other Education")
# Create the contingency table
table_resdim2_scenario1 <- table(df_filtered_resdim2_scenario1$RESDIM2, df_filtered_resdim2_scenario1$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_resdim2_scenario1) <- c("Strongly Disagree", "Strongly Agree")
# Perform the Chi-Squared test
chi_result_resdim2_scenario1 <- chisq.test(table_resdim2_scenario1)
# Calculate the odds ratio and confidence interval
odds_ratio_resdim2_scenario1 <- oddsratio(table_resdim2_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(knitr::kable(table_resdim2_scenario1, caption = "Contingency Table: Health and Science vs. Other Education vs. Belief in Solving Antibiotic Resistance (Strongly Disagree vs. Strongly Agree)"))
print(chi_result_resdim2_scenario1)
print(odds_ratio_resdim2_scenario1)


# Scenario 2: Neither Agree Nor Disagree vs. Strongly Disagree
# Load dataframe
df <- Database_simplified
df_filtered_resdim2_scenario2 <- df[df$RESDIM2 %in% c(1, 2), ]
# Create the HEALTH_SCIENCE variable
df_filtered_resdim2_scenario2$HEALTH_SCIENCE <- ifelse(df_filtered_resdim2_scenario2$PROF11 == 0 | df_filtered_resdim2_scenario2$PROF12 == 0, "Health and Science", "Other Education")
# Create the contingency table
table_resdim2_scenario2 <- table(df_filtered_resdim2_scenario2$RESDIM2, df_filtered_resdim2_scenario2$HEALTH_SCIENCE)
# Add descriptive labels
rownames(table_resdim2_scenario2) <- c("Strongly Disagree", "Neither Agree Nor Disagree")
# Perform the Chi-Squared test
chi_result_resdim2_scenario2 <- chisq.test(table_resdim2_scenario2)
# Calculate odds ratio and confidence interval
odds_ratio_resdim2_scenario2 <- oddsratio(table_resdim2_scenario2, conf.level = 0.95)$measure
# Print the table and results
print(knitr::kable(table_resdim2_scenario2, caption = "Contingency Table: Health and Science vs. Other Education vs. Belief in Solving Antibiotic Resistance (Strongly Disagree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim2_scenario2)
print(odds_ratio_resdim2_scenario2)


# Scenario 3: Strongly Agree + Neither Agree Nor Disagree vs. Strongly Disagree
# Load dataframe
df <- Database_simplified
df_filtered_resdim2_scenario3 <- df[df$RESDIM2 %in% c(1, 2, 3), ]
# Create the HEALTH_SCIENCE variable
df_filtered_resdim2_scenario3$HEALTH_SCIENCE <- ifelse(df_filtered_resdim2_scenario3$PROF11 == 0 | df_filtered_resdim2_scenario3$PROF12 == 0, "Health and Science", "Other Education")
# Categorize responses
df_filtered_resdim2_scenario3$Agree_Neither <- df_filtered_resdim2_scenario3$RESDIM2 %in% c(2, 3)
# Create the contingency table
table_resdim2_scenario3 <- table(df_filtered_resdim2_scenario3$Agree_Neither, df_filtered_resdim2_scenario3$HEALTH_SCIENCE)
# Add descriptive labels
rownames(table_resdim2_scenario3) <- c("Strongly Disagree", "Strongly Agree + Neither")
# Perform the Chi-Squared test
chi_result_resdim2_scenario3 <- chisq.test(table_resdim2_scenario3)
# Calculate odds ratio and confidence interval
odds_ratio_resdim2_scenario3 <- oddsratio(table_resdim2_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(knitr::kable(table_resdim2_scenario3, caption = "Contingency Table: Health and Science vs. Other Education vs. Belief in Solving Antibiotic Resistance (Strongly Disagree vs. Strongly Agree + Neither Agree Nor Disagree)"))
print(chi_result_resdim2_scenario3)
print(odds_ratio_resdim2_scenario3)


----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM3= Everyone needs to use antibiotics responsibly
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_resdim3_scenario1 <- df[df$RESDIM3 %in% c(1, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_resdim3_scenario1$HEALTH_SCIENCE <- ifelse(df_filtered_resdim3_scenario1$PROF11 == 0 | df_filtered_resdim3_scenario1$PROF12 == 0, "Health and Science", "Other Education")
# Create the contingency table
table_resdim3_scenario1 <- table(df_filtered_resdim3_scenario1$RESDIM3, df_filtered_resdim3_scenario1$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_resdim3_scenario1) <- c("Strongly Disagree", "Strongly Agree")
# Perform the Chi-Squared test
chi_result_resdim3_scenario1 <- chisq.test(table_resdim3_scenario1)
# Calculate the odds ratio and confidence interval
odds_ratio_resdim3_scenario1 <- oddsratio(table_resdim3_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(knitr::kable(table_resdim3_scenario1, caption = "Contingency Table: Health and Science vs. Other Education vs. Everyone needs to use antibiotics responsibly (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_resdim3_scenario1)
print(odds_ratio_resdim3_scenario1)


# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_resdim3_scenario2 <- df[df$RESDIM3 %in% c(2, 3), ]
# Create the HEALTH_SCIENCE variable
df_filtered_resdim3_scenario2$HEALTH_SCIENCE <- ifelse(df_filtered_resdim3_scenario2$PROF11 == 0 | df_filtered_resdim3_scenario2$PROF12 == 0, "Health and Science", "Other Education")
# Create the contingency table
table_resdim3_scenario2 <- table(df_filtered_resdim3_scenario2$RESDIM3, df_filtered_resdim3_scenario2$HEALTH_SCIENCE)
# Add descriptive labels
rownames(table_resdim3_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
# Perform the Chi-Squared test
chi_result_resdim3_scenario2 <- chisq.test(table_resdim3_scenario2)
# Calculate odds ratio and confidence interval
odds_ratio_resdim3_scenario2 <- oddsratio(table_resdim3_scenario2, conf.level = 0.95)$measure
# Print the table and results
print(knitr::kable(table_resdim3_scenario2, caption = "Contingency Table: Health and Science vs. Other Education vs. Everyone needs to use antibiotics responsibly (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim3_scenario2)
print(odds_ratio_resdim3_scenario2)


# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_resdim3_scenario3 <- df[df$RESDIM3 %in% c(1, 2, 3), ]
# Create the HEALTH_SCIENCE variable
df_filtered_resdim3_scenario3$HEALTH_SCIENCE <- ifelse(df_filtered_resdim3_scenario3$PROF11 == 0 | df_filtered_resdim3_scenario3$PROF12 == 0, "Health and Science", "Other Education")
# Categorize responses
df_filtered_resdim3_scenario3$Disagree_Neither <- df_filtered_resdim3_scenario3$RESDIM3 %in% c(1, 2)
# Create the contingency table
table_resdim3_scenario3 <- table(df_filtered_resdim3_scenario3$Disagree_Neither, df_filtered_resdim3_scenario3$HEALTH_SCIENCE)
# Add descriptive labels
rownames(table_resdim3_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
# Perform the Chi-Squared test
chi_result_resdim3_scenario3 <- chisq.test(table_resdim3_scenario3)
# Calculate odds ratio and confidence interval
odds_ratio_resdim3_scenario3 <- oddsratio(table_resdim3_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(knitr::kable(table_resdim3_scenario3, caption = "Contingency Table: Health and Science vs. Other Education vs. Everyone needs to use antibiotics responsibly (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_resdim3_scenario3)
print(odds_ratio_resdim3_scenario3)




----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM4= People like me can't do much to stop antibiotic resistance
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Agree vs. Strongly Disagree
# Load dataframe
df <- Database_simplified
df_filtered_resdim4_scenario1 <- df[df$RESDIM4 %in% c(1, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_resdim4_scenario1$HEALTH_SCIENCE <- ifelse(df_filtered_resdim4_scenario1$PROF11 == 0 | df_filtered_resdim4_scenario1$PROF12 == 0, "Health and Science", "Other Education")
# Create the contingency table
table_resdim4_scenario1 <- table(df_filtered_resdim4_scenario1$RESDIM4, df_filtered_resdim4_scenario1$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_resdim4_scenario1) <- c("Strongly Disagree", "Strongly Agree")
# Perform the Chi-Squared test
chi_result_resdim4_scenario1 <- chisq.test(table_resdim4_scenario1)
# Calculate the odds ratio and confidence interval
odds_ratio_resdim4_scenario1 <- oddsratio(table_resdim4_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(knitr::kable(table_resdim4_scenario1, caption = "Contingency Table: Health and Science vs. Other Education vs. Belief in Individual Impact on Antibiotic Resistance (Strongly Disagree vs. Strongly Agree)"))
print(chi_result_resdim4_scenario1)
print(odds_ratio_resdim4_scenario1)


# Scenario 2: Neither Agree Nor Disagree vs. Strongly Disagree
# Load dataframe
df <- Database_simplified
df_filtered_resdim4_scenario2 <- df[df$RESDIM4 %in% c(1, 2), ]
# Create the HEALTH_SCIENCE variable
df_filtered_resdim4_scenario2$HEALTH_SCIENCE <- ifelse(df_filtered_resdim4_scenario2$PROF11 == 0 | df_filtered_resdim4_scenario2$PROF12 == 0, "Health and Science", "Other Education")
# Create the contingency table
table_resdim4_scenario2 <- table(df_filtered_resdim4_scenario2$RESDIM4, df_filtered_resdim4_scenario2$HEALTH_SCIENCE)
# Add descriptive labels
rownames(table_resdim4_scenario2) <- c("Strongly Disagree", "Neither Agree Nor Disagree")
# Perform the Chi-Squared test
chi_result_resdim4_scenario2 <- chisq.test(table_resdim4_scenario2)
# Calculate odds ratio and confidence interval
odds_ratio_resdim4_scenario2 <- oddsratio(table_resdim4_scenario2, conf.level = 0.95)$measure
# Print the table and results
print(knitr::kable(table_resdim4_scenario2, caption = "Contingency Table: Health and Science vs. Other Education vs. Belief in Individual Impact on Antibiotic Resistance (Strongly Disagree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim4_scenario2)
print(odds_ratio_resdim4_scenario2)


# Scenario 3: Strongly Agree + Neither Agree Nor Disagree vs. Strongly Disagree
# Load dataframe
df <- Database_simplified
df_filtered_resdim4_scenario3 <- df[df$RESDIM4 %in% c(1, 2, 3), ]
# Create the HEALTH_SCIENCE variable
df_filtered_resdim4_scenario3$HEALTH_SCIENCE <- ifelse(df_filtered_resdim4_scenario3$PROF11 == 0 | df_filtered_resdim4_scenario3$PROF12 == 0, "Health and Science", "Other Education")
# Categorize responses
df_filtered_resdim4_scenario3$Agree_Neither <- df_filtered_resdim4_scenario3$RESDIM4 %in% c(2, 3)
# Create the contingency table
table_resdim4_scenario3 <- table(df_filtered_resdim4_scenario3$Agree_Neither, df_filtered_resdim4_scenario3$HEALTH_SCIENCE)
# Add descriptive labels
rownames(table_resdim4_scenario3) <- c("Strongly Disagree", "Strongly Agree + Neither")
# Perform the Chi-Squared test
chi_result_resdim4_scenario3 <- chisq.test(table_resdim4_scenario3)
# Calculate odds ratio and confidence interval
odds_ratio_resdim4_scenario3 <- oddsratio(table_resdim4_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(knitr::kable(table_resdim4_scenario3, caption = "Contingency Table: Health and Science vs. Other Education vs. Belief in Individual Impact on Antibiotic Resistance (Strongly Disagree vs. Strongly Agree + Neither Agree Nor Disagree)"))
print(chi_result_resdim4_scenario3)
print(odds_ratio_resdim4_scenario3)

----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM5= I am worried about the impact that antibiotic resistance will have on my health and that of my family
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Disagree vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_resdim5_scenario1 <- df[df$RESDIM5 %in% c(1, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_resdim5_scenario1$HEALTH_SCIENCE <- ifelse(df_filtered_resdim5_scenario1$PROF11 == 0 | df_filtered_resdim5_scenario1$PROF12 == 0, "Health and Science", "Other Education")
# Create the contingency table
table_resdim5_scenario1 <- table(df_filtered_resdim5_scenario1$RESDIM5, df_filtered_resdim5_scenario1$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_resdim5_scenario1) <- c("Strongly Disagree", "Strongly Agree")
# Perform the Chi-Squared test
chi_result_resdim5_scenario1 <- chisq.test(table_resdim5_scenario1)
# Calculate the odds ratio and confidence interval
odds_ratio_resdim5_scenario1 <- oddsratio(table_resdim5_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(knitr::kable(table_resdim5_scenario1, caption = "Contingency Table: Health and Science vs. Other Education vs. Impact of AMR on personal health and that of their family (Strongly Agree vs. Strongly Disagree)"))
print(chi_result_resdim5_scenario1)
print(odds_ratio_resdim5_scenario1)


# Scenario 2: Neither Agree Nor Disagree vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_resdim5_scenario2 <- df[df$RESDIM5 %in% c(2, 3), ]
# Create the HEALTH_SCIENCE variable
df_filtered_resdim5_scenario2$HEALTH_SCIENCE <- ifelse(df_filtered_resdim5_scenario2$PROF11 == 0 | df_filtered_resdim5_scenario2$PROF12 == 0, "Health and Science", "Other Education")
# Create the contingency table
table_resdim5_scenario2 <- table(df_filtered_resdim5_scenario2$RESDIM5, df_filtered_resdim5_scenario2$HEALTH_SCIENCE)
# Add descriptive labels
rownames(table_resdim5_scenario2) <- c("Neither Agree Nor Disagree", "Strongly Agree")
# Perform the Chi-Squared test
chi_result_resdim5_scenario2 <- chisq.test(table_resdim5_scenario2)
# Calculate odds ratio and confidence interval
odds_ratio_resdim5_scenario2 <- oddsratio(table_resdim5_scenario2, conf.level = 0.95)$measure
# Print the table and results
print(knitr::kable(table_resdim5_scenario2, caption = "Contingency Table: Health and Science vs. Other Education vs. Impact of AMR on personal health and that of their family (Strongly Agree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim5_scenario2)
print(odds_ratio_resdim5_scenario2)


# Scenario 3: Strongly Disagree + Neither Agree Nor Disagree vs. Strongly Agree
# Load dataframe
df <- Database_simplified
df_filtered_resdim5_scenario3 <- df[df$RESDIM5 %in% c(1, 2, 3), ]
# Create the HEALTH_SCIENCE variable
df_filtered_resdim5_scenario3$HEALTH_SCIENCE <- ifelse(df_filtered_resdim5_scenario3$PROF11 == 0 | df_filtered_resdim5_scenario3$PROF12 == 0, "Health and Science", "Other Education")
# Categorize responses
df_filtered_resdim5_scenario3$Disagree_Neither <- df_filtered_resdim5_scenario3$RESDIM5 %in% c(1, 2)
# Create the contingency table
table_resdim5_scenario3 <- table(df_filtered_resdim5_scenario3$Disagree_Neither, df_filtered_resdim5_scenario3$HEALTH_SCIENCE)
# Add descriptive labels
rownames(table_resdim5_scenario3) <- c("Strongly Agree", "Strongly Disagree + Neither")
# Perform the Chi-Squared test
chi_result_resdim5_scenario3 <- chisq.test(table_resdim5_scenario3)
# Calculate odds ratio and confidence
# Calculate odds ratio and confidence interval
odds_ratio_resdim5_scenario3 <- oddsratio(table_resdim5_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(knitr::kable(table_resdim5_scenario3, caption = "Contingency Table: Health and Science vs. Other Education vs. Impact of AMR on personal health and that of their family (Strongly Agree vs. Strongly Disagree + Neither Agree Nor Disagree)"))
print(chi_result_resdim5_scenario3)
print(odds_ratio_resdim5_scenario3)

----------------------------------------------------------------------------------------------------------------------
  
  ##RESDIM6= I am not at risk of getting an antibiotic-resistant infection, as long as I take my antibiotics correctly
  
  Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified dataframe
df <- Database_simplified

# Scenario 1: Strongly Agree vs. Strongly Disagree
# Load dataframe
df <- Database_simplified
df_filtered_resdim6_scenario1 <- df[df$RESDIM6 %in% c(1, 3), ]
# Create the HEALTH_SCIENCE variable based on PROF11 and PROF12
df_filtered_resdim6_scenario1$HEALTH_SCIENCE <- ifelse(df_filtered_resdim6_scenario1$PROF11 == 0 | df_filtered_resdim6_scenario1$PROF12 == 0, "Health and Science", "Other Education")
# Create the contingency table
table_resdim6_scenario1 <- table(df_filtered_resdim6_scenario1$RESDIM6, df_filtered_resdim6_scenario1$HEALTH_SCIENCE)
# Add descriptive labels to the rows
rownames(table_resdim6_scenario1) <- c("Strongly Disagree", "Strongly Agree")
# Perform the Chi-Squared test
chi_result_resdim6_scenario1 <- chisq.test(table_resdim6_scenario1)
# Calculate the odds ratio and confidence interval
odds_ratio_resdim6_scenario1 <- oddsratio(table_resdim6_scenario1, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(knitr::kable(table_resdim6_scenario1, caption = "Contingency Table: Health and Science vs. Other Education vs. Perception of Risk of Antibiotic-Resistant Infection (Strongly Disagree vs. Strongly Agree)"))
print(chi_result_resdim6_scenario1)
print(odds_ratio_resdim6_scenario1)


# Scenario 2: Neither Agree Nor Disagree vs. Strongly Disagree
# Load dataframe
df <- Database_simplified
df_filtered_resdim6_scenario2 <- df[df$RESDIM6 %in% c(1, 2), ]
# Create the HEALTH_SCIENCE variable
df_filtered_resdim6_scenario2$HEALTH_SCIENCE <- ifelse(df_filtered_resdim6_scenario2$PROF11 == 0 | df_filtered_resdim6_scenario2$PROF12 == 0, "Health and Science", "Other Education")
# Create the contingency table
table_resdim6_scenario2 <- table(df_filtered_resdim6_scenario2$RESDIM6, df_filtered_resdim6_scenario2$HEALTH_SCIENCE)
# Add descriptive labels
rownames(table_resdim6_scenario2) <- c("Strongly Disagree", "Neither Agree Nor Disagree")
# Perform the Chi-Squared test
chi_result_resdim6_scenario2 <- chisq.test(table_resdim6_scenario2)
# Calculate odds ratio and confidence interval
odds_ratio_resdim6_scenario2 <- oddsratio(table_resdim6_scenario2, conf.level = 0.95)$measure
# Print the table and results
print(knitr::kable(table_resdim6_scenario2, caption = "Contingency Table: Health and Science vs. Other Education vs. Perception of Risk of Antibiotic-Resistant Infection (Strongly Disagree vs. Neither Agree Nor Disagree)"))
print(chi_result_resdim6_scenario2)
print(odds_ratio_resdim6_scenario2)


# Scenario 3: Strongly Agree + Neither Agree Nor Disagree vs. Strongly Disagree
# Load dataframe
df <- Database_simplified
df_filtered_resdim6_scenario3 <- df[df$RESDIM6 %in% c(1, 2, 3), ]
# Create the HEALTH_SCIENCE variable
df_filtered_resdim6_scenario3$HEALTH_SCIENCE <- ifelse(df_filtered_resdim6_scenario3$PROF11 == 0 | df_filtered_resdim6_scenario3$PROF12 == 0, "Health and Science", "Other Education")
# Categorize responses
df_filtered_resdim6_scenario3$Agree_Neither <- df_filtered_resdim6_scenario3$RESDIM6 %in% c(2, 3)
# Create the contingency table
table_resdim6_scenario3 <- table(df_filtered_resdim6_scenario3$Agree_Neither, df_filtered_resdim6_scenario3$HEALTH_SCIENCE)
# Add descriptive labels
rownames(table_resdim6_scenario3) <- c("Strongly Disagree", "Strongly Agree + Neither")
# Perform the Chi-Squared test
chi_result_resdim6_scenario3 <- chisq.test(table_resdim6_scenario3)
# Calculate odds ratio and
# Calculate odds ratio and confidence interval
odds_ratio_resdim6_scenario3 <- oddsratio(table_resdim6_scenario3, conf.level = 0.95)$measure
# Print the formatted contingency table and results
print(knitr::kable(table_resdim6_scenario3, caption = "Contingency Table: Health and Science vs. Other Education vs. Perception of Risk of Antibiotic-Resistant Infection (Strongly Disagree vs. Strongly Agree + Neither Agree Nor Disagree)"))
print(chi_result_resdim6_scenario3)
print(odds_ratio_resdim6_scenario3)

########################################################## Multivariate Analysis #############################
# Load necessary packages
install.packages("car")
library(car)
install.packages("readxl")
library(readxl)

#Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified into a dataframe
df <- Database_simplified

###### CUSIN1 ########

# Preparing the variables
df$CUSIN1 <- as.factor(ifelse(df$CUSIN2 %in% c(0, 1), df$CUSIN1, NA)) # Keep only Yes (0) and No (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Removing rows with NA in the variables of interest 
df <- na.omit(df)

# Building the logistic regression model
model <- glm(CUSIN1 ~ AGE + HEALTH_SCIENCE, data = df, family = binomial())

# Checking the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

# Alternative model with only AGE for CUSIN1
alternative_model1_CUSIN1 <- glm(CUSIN1 ~ AGE, data = df, family = binomial())

# Alternative model with only HEALTH_SCIENCE for CUSIN1
alternative_model2_CUSIN1 <- glm(CUSIN1 ~ HEALTH_SCIENCE, data = df, family = binomial())

# Compare AIC of the main model with the alternative models
aic_values_CUSIN1 <- AIC(model, alternative_model1_CUSIN1, alternative_model2_CUSIN1)
print(aic_values_CUSIN1)

###### CUSIN2 #######

#Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified into a dataframe
df <- Database_simplified

# Preparing the variables
df$CUSIN2 <- as.factor(ifelse(df$CUSIN2 %in% c(0, 1), df$CUSIN2, NA)) # Keep only Yes (0) and No (1)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Femme (0) and Homme (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Removing rows with NA in the variables of interest 
df <- na.omit(df)

# Building the logistic regression model
model <- glm(CUSIN2 ~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df, family = binomial())

# Checking the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

# Model with only GENRE and AGE
alternative_model1 <- glm(CUSIN2 ~ GENRE + AGE, data = df, family = binomial())

# Model with only GENRE and NIVSCOL
alternative_model2 <- glm(CUSIN2 ~ GENRE + NIVSCOL, data = df, family = binomial())

# Model with only AGE and NIVSCOL
alternative_model3 <- glm(CUSIN2 ~ AGE + NIVSCOL, data = df, family = binomial())

# Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(CUSIN2 ~ GENRE + AGE + NIVSCOL, data = df, family = binomial())

# Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(CUSIN2 ~ GENRE + HEALTH_SCIENCE, data = df, family = binomial())

# Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(CUSIN2 ~ AGE + HEALTH_SCIENCE, data = df, family = binomial())

# Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(CUSIN2 ~ NIVSCOL + HEALTH_SCIENCE, data = df, family = binomial())

# Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3, 
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)
print(aic_values)


###### CUSIN3 #######

#Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified into a dataframe
df <- Database_simplified

# Preparing the variables
df$CUSIN3 <- as.factor(ifelse(df$CUSIN3 %in% c(0, 1), df$CUSIN3, NA)) # Keep only Yes (0) and No (1)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Femme (0) and Homme (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Removing rows with NA in the variables of interest 
df <- na.omit(df)

# Building the logistic regression model
model <- glm(CUSIN3 ~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df, family = binomial())

# Checking the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

# Model with only GENRE and AGE
alternative_model1 <- glm(CUSIN3 ~ GENRE + AGE, data = df, family = binomial())

# Model with only GENRE and NIVSCOL
alternative_model2 <- glm(CUSIN3 ~ GENRE + NIVSCOL, data = df, family = binomial())

# Model with only AGE and NIVSCOL
alternative_model3 <- glm(CUSIN3 ~ AGE + NIVSCOL, data = df, family = binomial())

# Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(CUSIN3 ~ GENRE + AGE + NIVSCOL, data = df, family = binomial())

# Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(CUSIN3 ~ GENRE + HEALTH_SCIENCE, data = df, family = binomial())

# Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(CUSIN3 ~ AGE + HEALTH_SCIENCE, data = df, family = binomial())

# Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(CUSIN3 ~ NIVSCOL + HEALTH_SCIENCE, data = df, family = binomial())

# Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3, 
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)
print(aic_values)


###### CUSIN4 #######

#Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified into a dataframe
df <- Database_simplified

# Preparing the variables
df$CUSIN4 <- as.factor(ifelse(df$CUSIN4 %in% c(0, 1), df$CUSIN4, NA)) # Keep only Yes (0) and No (1)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Femme (0) and Homme (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Removing rows with NA in the variables of interest 
df <- na.omit(df)

# Building the logistic regression model
model <- glm(CUSIN4 ~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df, family = binomial())

# Checking the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

# Model with only GENRE and AGE
alternative_model1 <- glm(CUSIN4 ~ GENRE + AGE, data = df, family = binomial())

# Model with only GENRE and NIVSCOL
alternative_model2 <- glm(CUSIN4 ~ GENRE + NIVSCOL, data = df, family = binomial())

# Model with only AGE and NIVSCOL
alternative_model3 <- glm(CUSIN4 ~ AGE + NIVSCOL, data = df, family = binomial())

# Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(CUSIN4 ~ GENRE + AGE + NIVSCOL, data = df, family = binomial())

# Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(CUSIN4 ~ GENRE + HEALTH_SCIENCE, data = df, family = binomial())

# Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(CUSIN4 ~ AGE + HEALTH_SCIENCE, data = df, family = binomial())

# Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(CUSIN4 ~ NIVSCOL + HEALTH_SCIENCE, data = df, family = binomial())

# Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3, 
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)
print(aic_values)

###### CUSIN5 #######

#Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified into a dataframe
df <- Database_simplified

# Preparing the variables
df$CUSIN5 <- as.factor(ifelse(df$CUSIN5 %in% c(0, 1), df$CUSIN5, NA)) # Keep only Yes (0) and No (1)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Femme (0) and Homme (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))

# Removing rows with NA in the variables of interest 
df <- na.omit(df)

# Building the logistic regression model
model <- glm(CUSIN5 ~ GENRE + AGE + NIVSCOL , data = df, family = binomial())

# Checking the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

# Model with only GENRE and AGE
alternative_model1 <- glm(CUSIN5 ~ GENRE + AGE, data = df, family = binomial())

# Model with only GENRE and NIVSCOL
alternative_model2 <- glm(CUSIN5 ~ GENRE + NIVSCOL, data = df, family = binomial())

# Model with only AGE and NIVSCOL
alternative_model3 <- glm(CUSIN5 ~ AGE + NIVSCOL, data = df, family = binomial())

# Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(CUSIN5 ~ GENRE + AGE + NIVSCOL, data = df, family = binomial())

# Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3, 
                  alternative_model4)
print(aic_values)


###### CUSIN6 #######

#Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
#View(Database_simplified)
# Load the Database_simplified into a dataframe
df <- Database_simplified

# Preparing the variables
df$CUSIN6 <- as.factor(ifelse(df$CUSIN6 %in% c(0, 1), df$CUSIN6, NA)) # Keep only Yes (0) and No (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Removing rows with NA in the variables of interest 
df <- na.omit(df)

# Building the logistic regression model
model <- glm(CUSIN6 ~  AGE + NIVSCOL + HEALTH_SCIENCE , data = df, family = binomial())

# Checking the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

# Model with only AGE and NIVSCOL
alternative_model1 <- glm(CUSIN6 ~ AGE + NIVSCOL, data = df, family = binomial())

# Model with GENRE, AGE, and NIVSCOL
alternative_model2 <- glm(CUSIN6 ~ GENRE + AGE + NIVSCOL, data = df, family = binomial())

# Model with AGE and HEALTH_SCIENCE
alternative_model3 <- glm(CUSIN6 ~ AGE + HEALTH_SCIENCE, data = df, family = binomial())

# Model with NIVSCOL and HEALTH_SCIENCE
alternative_model4 <- glm(CUSIN6 ~ NIVSCOL + HEALTH_SCIENCE, data = df, family = binomial())


# Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3, 
                  alternative_model4)
print(aic_values)


###### PRESCATB1 #######

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$PRESCATB1 <- as.factor(ifelse(df$PRESCATB1 %in% c(0, 1, 3), df$PRESCATB1, NA)) # Keep only Yes (0), No (1), and Sometimes (3)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Create a combined 'No_Sometimes' variable for PRESCATB1
df$No_Sometimes <- df$PRESCATB1 %in% c(1, 3)

# Remove rows with NA in the variables of interest
df <- na.omit(df)

# Build the logistic regression model
model <- glm(No_Sometimes ~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

# Model with only GENRE and AGE
alternative_model1 <- glm(No_Sometimes ~ GENRE + AGE, data = df, family = binomial())

# Model with only GENRE and NIVSCOL
alternative_model2 <- glm(No_Sometimes ~ GENRE + NIVSCOL, data = df, family = binomial())

# Model with only AGE and NIVSCOL
alternative_model3 <- glm(No_Sometimes ~ AGE + NIVSCOL, data = df, family = binomial())

# Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(No_Sometimes ~ GENRE + AGE + NIVSCOL, data = df, family = binomial())

# Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(No_Sometimes ~ GENRE + HEALTH_SCIENCE, data = df, family = binomial())

# Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(No_Sometimes ~ AGE + HEALTH_SCIENCE, data = df, family = binomial())

# Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(No_Sometimes ~ NIVSCOL + HEALTH_SCIENCE, data = df, family = binomial())

# Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3, 
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)
print(aic_values)

#### ARRETATB ####

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$ARRETATB <- as.factor(ifelse(df$ARRETATB %in% c(0, 2), df$ARRETATB, NA)) #Keep only Always (0) and Sometimes (2)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Create a combined 'Sometimes_Always' variable for ARRETATB
df$Sometimes_Always <- df$ARRETATB %in% c(0, 2)

# Remove rows with NA in the variables of interest
df <- na.omit(df)

# Build the logistic regression model
model <- glm(Sometimes_Always ~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

#### ATBORAL ####

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$ATBORAL1 <- as.factor(ifelse(df$ATBORAL1 %in% c(0, 1), df$ATBORAL1, NA)) # Keep only Yes (0) and No (1)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'Yes' and 'No' in ATBORAL1
df_filtered_atboral1 <- df[df$ATBORAL1 %in% c(0, 1), ]

# Remove rows with NA in the variables of interest
df_filtered_atboral1 <- na.omit(df_filtered_atboral1)

# Build the logistic regression model
model <- glm(ATBORAL1 ~ GENRE + AGE + HEALTH_SCIENCE, data = df_filtered_atboral1, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

#Fit alternative models for AIC comparison
#Model with only GENRE and AGE
alternative_model1 <- glm(ATBORAL1 ~ GENRE + AGE, data = df_filtered_atboral1, family = binomial())

#Model with GENRE and HEALTH_SCIENCE
alternative_model2 <- glm(ATBORAL1 ~ GENRE + HEALTH_SCIENCE, data = df_filtered_atboral1, family = binomial())

#Model with AGE and HEALTH_SCIENCE
alternative_model3 <- glm(ATBORAL1 ~ AGE + HEALTH_SCIENCE, data = df_filtered_atboral1, family = binomial())

#Model with NIVSCOL and HEALTH_SCIENCE
alternative_model4 <- glm(ATBORAL1 ~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_atboral1, family = binomial())

#Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3,
                  alternative_model4)
print(aic_values)

##### ATBANI1 ####

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$ATBANI1 <- as.factor(ifelse(df$ATBANI1 %in% c(0, 1), df$ATBANI1, NA)) # Keep only True (0) and False (1)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'True' and 'False' in ATBANI1
df_filtered_atbani1 <- df[df$ATBANI1 %in% c(0, 1), ]

# Remove rows with NA in the variables of interest
df_filtered_atbani1 <- na.omit(df_filtered_atbani1)

# Build the logistic regression model
model <- glm(ATBANI1 ~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_atbani1, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

# Model with only GENRE and AGE
alternative_model1 <- glm(ATBANI1 ~ GENRE + AGE, data = df_filtered_atbani1, family = binomial())

# Model with only GENRE and NIVSCOL
alternative_model2 <- glm(ATBANI1 ~ GENRE + NIVSCOL, data = df_filtered_atbani1, family = binomial())

# Model with only AGE and NIVSCOL
alternative_model3 <- glm(ATBANI1 ~ AGE + NIVSCOL, data = df_filtered_atbani1, family = binomial())

# Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(ATBANI1 ~ GENRE + AGE + NIVSCOL, data = df_filtered_atbani1, family = binomial())

# Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(ATBANI1 ~ GENRE + HEALTH_SCIENCE, data = df_filtered_atbani1, family = binomial())

# Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(ATBANI1 ~ AGE + HEALTH_SCIENCE, data = df_filtered_atbani1, family = binomial())

# Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(ATBANI1 ~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_atbani1, family = binomial())

# Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3, 
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)
print(aic_values)
                  
#### ATBANI2 ####

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$ATBANI2 <- as.factor(ifelse(df$ATBANI2 %in% c(0, 1), df$ATBANI2, NA)) # Keep only True (0) and False (1)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'True' and 'False' in ATBANI2
df_filtered_atbani2 <- df[df$ATBANI2 %in% c(0, 1), ]

# Remove rows with NA in the variables of interest
df_filtered_atbani2 <- na.omit(df_filtered_atbani2)

# Build the logistic regression model
model <- glm(ATBANI2 ~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_atbani2, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

# Model with only GENRE and AGE
alternative_model1 <- glm(ATBANI2 ~ GENRE + AGE, data = df_filtered_atbani2, family = binomial())

# Model with only GENRE and NIVSCOL
alternative_model2 <- glm(ATBANI2 ~ GENRE + NIVSCOL, data = df_filtered_atbani2, family = binomial())

# Model with only AGE and NIVSCOL
alternative_model3 <- glm(ATBANI2 ~ AGE + NIVSCOL, data = df_filtered_atbani2, family = binomial())

# Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(ATBANI2 ~ GENRE + AGE + NIVSCOL, data = df_filtered_atbani2, family = binomial())

# Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(ATBANI2 ~ GENRE + HEALTH_SCIENCE, data = df_filtered_atbani2, family = binomial())

# Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(ATBANI2 ~ AGE + HEALTH_SCIENCE, data = df_filtered_atbani2, family = binomial())

# Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(ATBANI2 ~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_atbani2, family = binomial())

# Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3, 
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)

print(aic_values)


#### ATBANI3 ####

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$ATBANI3 <- as.factor(ifelse(df$ATBANI3 %in% c(0, 1), df$ATBANI3, NA)) # Keep only True (0) and False (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'True' and 'False' in ATBANI3
df_filtered_ATBANI3 <- df[df$ATBANI3 %in% c(0, 1), ]

# Remove rows with NA in the variables of interest
df_filtered_ATBANI3 <- na.omit(df_filtered_ATBANI3)

# Build the logistic regression model
model <- glm(ATBANI3 ~ AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_ATBANI3, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

# Model with only AGE and NIVSCOL
alternative_model1 <- glm(ATBANI3 ~ AGE + NIVSCOL, data = df_filtered_ATBANI3, family = binomial())

# Model with AGE and HEALTH_SCIENCE
alternative_model2 <- glm(ATBANI3 ~ AGE + HEALTH_SCIENCE, data = df_filtered_ATBANI3, family = binomial())

# Model with NIVSCOL and HEALTH_SCIENCE
alternative_model3 <- glm(ATBANI3 ~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_ATBANI3, family = binomial())

# Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3)

print(aic_values)

#### ATBANI4 ####

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$ATBANI4 <- as.factor(ifelse(df$ATBANI4 %in% c(0, 1), df$ATBANI4, NA)) # Keep only True (0) and False (1)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'True' and 'False' in ATBANI4
df_filtered_ATBANI4 <- df[df$ATBANI4 %in% c(0, 1), ]

# Remove rows with NA in the variables of interest
df_filtered_ATBANI4 <- na.omit(df_filtered_ATBANI4)

# Build the logistic regression model
model <- glm(ATBANI4 ~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_ATBANI4, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

# Model with only GENRE and AGE
alternative_model1 <- glm(ATBANI4 ~ GENRE + AGE, data = df_filtered_ATBANI4, family = binomial())

# Model with only GENRE and NIVSCOL
alternative_model2 <- glm(ATBANI4 ~ GENRE + NIVSCOL, data = df_filtered_ATBANI4, family = binomial())

# Model with only AGE and NIVSCOL
alternative_model3 <- glm(ATBANI4 ~ AGE + NIVSCOL, data = df_filtered_ATBANI4, family = binomial())

# Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(ATBANI4 ~ GENRE + AGE + NIVSCOL, data = df_filtered_ATBANI4, family = binomial())

# Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(ATBANI4 ~ GENRE + HEALTH_SCIENCE, data = df_filtered_ATBANI4, family = binomial())

# Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(ATBANI4 ~ AGE + HEALTH_SCIENCE, data = df_filtered_ATBANI4, family = binomial())

# Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(ATBANI4 ~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_ATBANI4, family = binomial())

# Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3, 
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)

print(aic_values)


#### RESATB1 ####

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$RESATB1 <- as.factor(ifelse(df$RESATB1 %in% c(0, 1), df$RESATB1, NA)) # Keep only True (0) and False (1)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'True' and 'False' in RESATB1
df_filtered_RESATB1 <- df[df$RESATB1 %in% c(0, 1), ]

# Remove rows with NA in the variables of interest
df_filtered_RESATB1 <- na.omit(df_filtered_RESATB1)

# Build the logistic regression model
model <- glm(RESATB1 ~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESATB1, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

# Model with only GENRE and AGE
alternative_model1 <- glm(RESATB1 ~ GENRE + AGE, data = df_filtered_RESATB1, family = binomial())

# Model with only GENRE and NIVSCOL
alternative_model2 <- glm(RESATB1 ~ GENRE + NIVSCOL, data = df_filtered_RESATB1, family = binomial())

# Model with only AGE and NIVSCOL
alternative_model3 <- glm(RESATB1 ~ AGE + NIVSCOL, data = df_filtered_RESATB1, family = binomial())

# Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(RESATB1 ~ GENRE + AGE + NIVSCOL, data = df_filtered_RESATB1, family = binomial())

# Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(RESATB1 ~ GENRE + HEALTH_SCIENCE, data = df_filtered_RESATB1, family = binomial())

# Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(RESATB1 ~ AGE + HEALTH_SCIENCE, data = df_filtered_RESATB1, family = binomial())

# Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(RESATB1 ~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESATB1, family = binomial())

# Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3, 
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)

print(aic_values)

#### RESATB2 ####

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$RESATB2 <- as.factor(ifelse(df$RESATB2 %in% c(0, 1), df$RESATB2, NA)) # Keep only True (0) and False (1)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'True' and 'False' in RESATB2
df_filtered_RESATB2 <- df[df$RESATB2 %in% c(0, 1), ]

# Remove rows with NA in the variables of interest
df_filtered_RESATB2 <- na.omit(df_filtered_RESATB2)

# Build the logistic regression model
model <- glm(RESATB2 ~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESATB2, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

# Model with only GENRE and AGE
alternative_model1 <- glm(RESATB2 ~ GENRE + AGE, data = df_filtered_RESATB2, family = binomial())

# Model with only GENRE and NIVSCOL
alternative_model2 <- glm(RESATB2 ~ GENRE + NIVSCOL, data = df_filtered_RESATB2, family = binomial())

# Model with only AGE and NIVSCOL
alternative_model3 <- glm(RESATB2 ~ AGE + NIVSCOL, data = df_filtered_RESATB2, family = binomial())

# Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(RESATB2 ~ GENRE + AGE + NIVSCOL, data = df_filtered_RESATB2, family = binomial())

# Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(RESATB2 ~ GENRE + HEALTH_SCIENCE, data = df_filtered_RESATB2, family = binomial())

# Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(RESATB2 ~ AGE + HEALTH_SCIENCE, data = df_filtered_RESATB2, family = binomial())

# Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(RESATB2 ~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESATB2, family = binomial())

# Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3, 
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)

print(aic_values)

#### RESATB3 ####

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$RESATB3 <- as.factor(ifelse(df$RESATB3 %in% c(0, 1), df$RESATB3, NA)) # Keep only True (0) and False (1)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'True' and 'False' in RESATB3
df_filtered_RESATB3 <- df[df$RESATB3 %in% c(0, 1), ]

# Remove rows with NA in the variables of interest
df_filtered_RESATB3 <- na.omit(df_filtered_RESATB3)

# Build the logistic regression model
model <- glm(RESATB3 ~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESATB3, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

# Model with only GENRE and AGE
alternative_model1 <- glm(RESATB3 ~ GENRE + AGE, data = df_filtered_RESATB3, family = binomial())

# Model with only GENRE and NIVSCOL
alternative_model2 <- glm(RESATB3 ~ GENRE + NIVSCOL, data = df_filtered_RESATB3, family = binomial())

# Model with only AGE and NIVSCOL
alternative_model3 <- glm(RESATB3 ~ AGE + NIVSCOL, data = df_filtered_RESATB3, family = binomial())

# Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(RESATB3 ~ GENRE + AGE + NIVSCOL, data = df_filtered_RESATB3, family = binomial())

# Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(RESATB3 ~ GENRE + HEALTH_SCIENCE, data = df_filtered_RESATB3, family = binomial())

# Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(RESATB3 ~ AGE + HEALTH_SCIENCE, data = df_filtered_RESATB3, family = binomial())

# Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(RESATB3 ~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESATB3, family = binomial())

# Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3, 
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)

print(aic_values)

#### RESATB4 ####

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$RESATB4 <- as.factor(ifelse(df$RESATB4 %in% c(0, 1), df$RESATB4, NA)) # Keep only True (0) and False (1)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'True' and 'False' in RESATB4
df_filtered_RESATB4 <- df[df$RESATB4 %in% c(0, 1), ]

# Remove rows with NA in the variables of interest
df_filtered_RESATB4 <- na.omit(df_filtered_RESATB4)

# Build the logistic regression model
model <- glm(RESATB4 ~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESATB4, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

# Model with only GENRE and AGE
alternative_model1 <- glm(RESATB4 ~ GENRE + AGE, data = df_filtered_RESATB4, family = binomial())

# Model with only GENRE and NIVSCOL
alternative_model2 <- glm(RESATB4 ~ GENRE + NIVSCOL, data = df_filtered_RESATB4, family = binomial())

# Model with only AGE and NIVSCOL
alternative_model3 <- glm(RESATB4 ~ AGE + NIVSCOL, data = df_filtered_RESATB4, family = binomial())

# Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(RESATB4 ~ GENRE + AGE + NIVSCOL, data = df_filtered_RESATB4, family = binomial())

# Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(RESATB4 ~ GENRE + HEALTH_SCIENCE, data = df_filtered_RESATB4, family = binomial())

# Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(RESATB4 ~ AGE + HEALTH_SCIENCE, data = df_filtered_RESATB4, family = binomial())

# Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(RESATB4 ~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESATB4, family = binomial())

# Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3, 
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)

print(aic_values)

#### RESATB5 ####

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$RESATB5 <- as.factor(ifelse(df$RESATB5 %in% c(0, 1), df$RESATB5, NA)) # Keep only True (0) and False (1)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'True' and 'False' in RESATB5
df_filtered_RESATB5 <- df[df$RESATB5 %in% c(0, 1), ]

# Remove rows with NA in the variables of interest
df_filtered_RESATB5 <- na.omit(df_filtered_RESATB5)

# Build the logistic regression model
model <- glm(RESATB5 ~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESATB5, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

# Model with only GENRE and AGE
alternative_model1 <- glm(RESATB5 ~ GENRE + AGE, data = df_filtered_RESATB5, family = binomial())

# Model with only GENRE and NIVSCOL
alternative_model2 <- glm(RESATB5 ~ GENRE + NIVSCOL, data = df_filtered_RESATB5, family = binomial())

# Model with only AGE and NIVSCOL
alternative_model3 <- glm(RESATB5 ~ AGE + NIVSCOL, data = df_filtered_RESATB5, family = binomial())

# Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(RESATB5 ~ GENRE + AGE + NIVSCOL, data = df_filtered_RESATB5, family = binomial())

# Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(RESATB5 ~ GENRE + HEALTH_SCIENCE, data = df_filtered_RESATB5, family = binomial())

# Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(RESATB5 ~ AGE + HEALTH_SCIENCE, data = df_filtered_RESATB5, family = binomial())

# Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(RESATB5 ~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESATB5, family = binomial())

# Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3, 
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)

print(aic_values)

#### RESATB6 ####

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$RESATB6 <- as.factor(ifelse(df$RESATB6 %in% c(0, 1), df$RESATB6, NA)) # Keep only True (0) and False (1)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'True' and 'False' in RESATB6
df_filtered_RESATB6 <- df[df$RESATB6 %in% c(0, 1), ]

# Remove rows with NA in the variables of interest
df_filtered_RESATB6 <- na.omit(df_filtered_RESATB6)

# Build the logistic regression model
model <- glm(RESATB6 ~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESATB6, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

# Model with only GENRE and AGE
alternative_model1 <- glm(RESATB6 ~ GENRE + AGE, data = df_filtered_RESATB6, family = binomial())

# Model with only GENRE and NIVSCOL
alternative_model2 <- glm(RESATB6 ~ GENRE + NIVSCOL, data = df_filtered_RESATB6, family = binomial())

# Model with only AGE and NIVSCOL
alternative_model3 <- glm(RESATB6 ~ AGE + NIVSCOL, data = df_filtered_RESATB6, family = binomial())

# Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(RESATB6 ~ GENRE + AGE + NIVSCOL, data = df_filtered_RESATB6, family = binomial())

# Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(RESATB6 ~ GENRE + HEALTH_SCIENCE, data = df_filtered_RESATB6, family = binomial())

# Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(RESATB6 ~ AGE + HEALTH_SCIENCE, data = df_filtered_RESATB6, family = binomial())

# Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(RESATB6 ~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESATB6, family = binomial())

# Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3, 
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)

print(aic_values)


#### RESATB7 ####

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$RESATB7 <- as.factor(ifelse(df$RESATB7 %in% c(0, 1), df$RESATB7, NA)) # Keep only True (0) and False (1)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'True' and 'False' in RESATB7
df_filtered_RESATB7 <- df[df$RESATB7 %in% c(0, 1), ]

# Remove rows with NA in the variables of interest
df_filtered_RESATB7 <- na.omit(df_filtered_RESATB7)

# Build the logistic regression model
model <- glm(RESATB7 ~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESATB7, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

# Model with only GENRE and AGE
alternative_model1 <- glm(RESATB7 ~ GENRE + AGE, data = df_filtered_RESATB7, family = binomial())

# Model with only GENRE and NIVSCOL
alternative_model2 <- glm(RESATB7 ~ GENRE + NIVSCOL, data = df_filtered_RESATB7, family = binomial())

# Model with only AGE and NIVSCOL
alternative_model3 <- glm(RESATB7 ~ AGE + NIVSCOL, data = df_filtered_RESATB7, family = binomial())

# Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(RESATB7 ~ GENRE + AGE + NIVSCOL, data = df_filtered_RESATB7, family = binomial())

# Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(RESATB7 ~ GENRE + HEALTH_SCIENCE, data = df_filtered_RESATB7, family = binomial())

# Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(RESATB7 ~ AGE + HEALTH_SCIENCE, data = df_filtered_RESATB7, family = binomial())

# Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(RESATB7 ~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESATB7, family = binomial())

# Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3, 
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)

print(aic_values)

#### RESATB8 ####

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$RESATB8 <- as.factor(ifelse(df$RESATB8 %in% c(0, 1), df$RESATB8, NA)) # Keep only True (0) and False (1)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'True' and 'False' in RESATB8
df_filtered_RESATB8 <- df[df$RESATB8 %in% c(0, 1), ]

# Remove rows with NA in the variables of interest
df_filtered_RESATB8 <- na.omit(df_filtered_RESATB8)

# Build the logistic regression model
model <- glm(RESATB8 ~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESATB8, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

# Model with only GENRE and AGE
alternative_model1 <- glm(RESATB8 ~ GENRE + AGE, data = df_filtered_RESATB8, family = binomial())

# Model with only GENRE and NIVSCOL
alternative_model2 <- glm(RESATB8 ~ GENRE + NIVSCOL, data = df_filtered_RESATB8, family = binomial())

# Model with only AGE and NIVSCOL
alternative_model3 <- glm(RESATB8 ~ AGE + NIVSCOL, data = df_filtered_RESATB8, family = binomial())

# Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(RESATB8 ~ GENRE + AGE + NIVSCOL, data = df_filtered_RESATB8, family = binomial())

# Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(RESATB8 ~ GENRE + HEALTH_SCIENCE, data = df_filtered_RESATB8, family = binomial())

# Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(RESATB8 ~ AGE + HEALTH_SCIENCE, data = df_filtered_RESATB8, family = binomial())

# Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(RESATB8 ~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESATB8, family = binomial())

# Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3, 
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)

print(aic_values)

#### ATBRGL1 #### 

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$ATBRGL1 <- as.factor(ifelse(df$ATBRGL1 %in% c(1, 2), df$ATBRGL1, NA)) # Keep only Strongly disagree (1) and Neither agree nor disagree (2)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'Strongly disagree' and 'Neither agree nor disagree' in ATBGRL1
df_filtered_atbrgl1 <- df[df$ATBRGL1 %in% c(1, 2), ]

# Remove rows with NA in the variables of interest
df_filtered_atbrgl1 <- na.omit(df_filtered_atbrgl1)

# Build the logistic regression model
model <- glm(ATBRGL1 ~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_atbrgl1, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

#Model with only GENRE and AGE
alternative_model1 <- glm(ATBRGL1 ~ GENRE + AGE, data = df_filtered_atbrgl1, family = binomial())

#Model with only GENRE and NIVSCOL
alternative_model2 <- glm(ATBRGL1 ~ GENRE + NIVSCOL, data = df_filtered_atbrgl1, family = binomial())

#Model with only AGE and NIVSCOL
alternative_model3 <- glm(ATBRGL1 ~ AGE + NIVSCOL, data = df_filtered_atbrgl1, family = binomial())

#Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(ATBRGL1 ~ GENRE + AGE + NIVSCOL, data = df_filtered_atbrgl1, family = binomial())

#Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(ATBRGL1 ~ GENRE + HEALTH_SCIENCE, data = df_filtered_atbrgl1, family = binomial())

#Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(ATBRGL1 ~ AGE + HEALTH_SCIENCE, data = df_filtered_atbrgl1, family = binomial())

#Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(ATBRGL1 ~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_atbrgl1, family = binomial())

#Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3,
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)
print(aic_values)

#### ATBRGL2#### 

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$ATBRGL2<- as.factor(ifelse(df$ATBRGL2%in% c(1, 2), df$ATBRGL2, NA)) # Keep only Strongly disagree (1) and Neither agree nor disagree (2)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'Strongly disagree' and 'Neither agree nor disagree' in ATBGRL1
df_filtered_ATBRGL2<- df[df$ATBRGL2%in% c(1, 2), ]

# Remove rows with NA in the variables of interest
df_filtered_ATBRGL2<- na.omit(df_filtered_ATBRGL2)

# Build the logistic regression model
model <- glm(ATBRGL2~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_ATBRGL2, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

#Model with only GENRE and AGE
alternative_model1 <- glm(ATBRGL2~ GENRE + AGE, data = df_filtered_ATBRGL2, family = binomial())

#Model with only GENRE and NIVSCOL
alternative_model2 <- glm(ATBRGL2~ GENRE + NIVSCOL, data = df_filtered_ATBRGL2, family = binomial())

#Model with only AGE and NIVSCOL
alternative_model3 <- glm(ATBRGL2~ AGE + NIVSCOL, data = df_filtered_ATBRGL2, family = binomial())

#Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(ATBRGL2~ GENRE + AGE + NIVSCOL, data = df_filtered_ATBRGL2, family = binomial())

#Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(ATBRGL2~ GENRE + HEALTH_SCIENCE, data = df_filtered_ATBRGL2, family = binomial())

#Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(ATBRGL2~ AGE + HEALTH_SCIENCE, data = df_filtered_ATBRGL2, family = binomial())

#Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(ATBRGL2~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_ATBRGL2, family = binomial())

#Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3,
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)
print(aic_values)

#### ATBRGL3#### 

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$ATBRGL3<- as.factor(ifelse(df$ATBRGL3%in% c(1, 2), df$ATBRGL3, NA)) # Keep only Strongly disagree (1) and Neither agree nor disagree (2)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'Strongly disagree' and 'Neither agree nor disagree' in ATBGRL1
df_filtered_ATBRGL3<- df[df$ATBRGL3%in% c(1, 2), ]

# Remove rows with NA in the variables of interest
df_filtered_ATBRGL3<- na.omit(df_filtered_ATBRGL3)

# Build the logistic regression model
model <- glm(ATBRGL3~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_ATBRGL3, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

#Model with only GENRE and AGE
alternative_model1 <- glm(ATBRGL3~ GENRE + AGE, data = df_filtered_ATBRGL3, family = binomial())

#Model with only GENRE and NIVSCOL
alternative_model2 <- glm(ATBRGL3~ GENRE + NIVSCOL, data = df_filtered_ATBRGL3, family = binomial())

#Model with only AGE and NIVSCOL
alternative_model3 <- glm(ATBRGL3~ AGE + NIVSCOL, data = df_filtered_ATBRGL3, family = binomial())

#Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(ATBRGL3~ GENRE + AGE + NIVSCOL, data = df_filtered_ATBRGL3, family = binomial())

#Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(ATBRGL3~ GENRE + HEALTH_SCIENCE, data = df_filtered_ATBRGL3, family = binomial())

#Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(ATBRGL3~ AGE + HEALTH_SCIENCE, data = df_filtered_ATBRGL3, family = binomial())

#Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(ATBRGL3~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_ATBRGL3, family = binomial())

#Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3,
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)
print(aic_values)

#### ATBRGL4#### 

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$ATBRGL4<- as.factor(ifelse(df$ATBRGL4%in% c(1, 2), df$ATBRGL4, NA)) # Keep only Strongly disagree (1) and Neither agree nor disagree (2)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'Strongly disagree' and 'Neither agree nor disagree' in ATBGRL1
df_filtered_ATBRGL4<- df[df$ATBRGL4%in% c(1, 2), ]

# Remove rows with NA in the variables of interest
df_filtered_ATBRGL4<- na.omit(df_filtered_ATBRGL4)

# Build the logistic regression model
model <- glm(ATBRGL4~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_ATBRGL4, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

#Model with only GENRE and AGE
alternative_model1 <- glm(ATBRGL4~ GENRE + AGE, data = df_filtered_ATBRGL4, family = binomial())

#Model with only GENRE and NIVSCOL
alternative_model2 <- glm(ATBRGL4~ GENRE + NIVSCOL, data = df_filtered_ATBRGL4, family = binomial())

#Model with only AGE and NIVSCOL
alternative_model3 <- glm(ATBRGL4~ AGE + NIVSCOL, data = df_filtered_ATBRGL4, family = binomial())

#Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(ATBRGL4~ GENRE + AGE + NIVSCOL, data = df_filtered_ATBRGL4, family = binomial())

#Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(ATBRGL4~ GENRE + HEALTH_SCIENCE, data = df_filtered_ATBRGL4, family = binomial())

#Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(ATBRGL4~ AGE + HEALTH_SCIENCE, data = df_filtered_ATBRGL4, family = binomial())

#Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(ATBRGL4~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_ATBRGL4, family = binomial())

#Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3,
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)
print(aic_values)

#### ATBRGL5#### 

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$ATBRGL5<- as.factor(ifelse(df$ATBRGL5%in% c(1, 2), df$ATBRGL5, NA)) # Keep only Strongly disagree (1) and Neither agree nor disagree (2)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'Strongly disagree' and 'Neither agree nor disagree' in ATBGRL1
df_filtered_ATBRGL5<- df[df$ATBRGL5%in% c(1, 2), ]

# Remove rows with NA in the variables of interest
df_filtered_ATBRGL5<- na.omit(df_filtered_ATBRGL5)

# Build the logistic regression model
model <- glm(ATBRGL5~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_ATBRGL5, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

#Model with only GENRE and AGE
alternative_model1 <- glm(ATBRGL5~ GENRE + AGE, data = df_filtered_ATBRGL5, family = binomial())

#Model with only GENRE and NIVSCOL
alternative_model2 <- glm(ATBRGL5~ GENRE + NIVSCOL, data = df_filtered_ATBRGL5, family = binomial())

#Model with only AGE and NIVSCOL
alternative_model3 <- glm(ATBRGL5~ AGE + NIVSCOL, data = df_filtered_ATBRGL5, family = binomial())

#Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(ATBRGL5~ GENRE + AGE + NIVSCOL, data = df_filtered_ATBRGL5, family = binomial())

#Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(ATBRGL5~ GENRE + HEALTH_SCIENCE, data = df_filtered_ATBRGL5, family = binomial())

#Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(ATBRGL5~ AGE + HEALTH_SCIENCE, data = df_filtered_ATBRGL5, family = binomial())

#Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(ATBRGL5~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_ATBRGL5, family = binomial())

#Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3,
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)
print(aic_values)

#### ATBRGL6#### 

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$ATBRGL6<- as.factor(ifelse(df$ATBRGL6%in% c(1, 2), df$ATBRGL6, NA)) # Keep only Strongly disagree (1) and Neither agree nor disagree (2)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'Strongly disagree' and 'Neither agree nor disagree' in ATBGRL1
df_filtered_ATBRGL6<- df[df$ATBRGL6%in% c(1, 2), ]

# Remove rows with NA in the variables of interest
df_filtered_ATBRGL6<- na.omit(df_filtered_ATBRGL6)

# Build the logistic regression model
model <- glm(ATBRGL6~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_ATBRGL6, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

#Model with only GENRE and AGE
alternative_model1 <- glm(ATBRGL6~ GENRE + AGE, data = df_filtered_ATBRGL6, family = binomial())

#Model with only GENRE and NIVSCOL
alternative_model2 <- glm(ATBRGL6~ GENRE + NIVSCOL, data = df_filtered_ATBRGL6, family = binomial())

#Model with only AGE and NIVSCOL
alternative_model3 <- glm(ATBRGL6~ AGE + NIVSCOL, data = df_filtered_ATBRGL6, family = binomial())

#Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(ATBRGL6~ GENRE + AGE + NIVSCOL, data = df_filtered_ATBRGL6, family = binomial())

#Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(ATBRGL6~ GENRE + HEALTH_SCIENCE, data = df_filtered_ATBRGL6, family = binomial())

#Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(ATBRGL6~ AGE + HEALTH_SCIENCE, data = df_filtered_ATBRGL6, family = binomial())

#Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(ATBRGL6~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_ATBRGL6, family = binomial())

#Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3,
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)
print(aic_values)

#### ATBRGL7#### 

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$ATBRGL7<- as.factor(ifelse(df$ATBRGL7%in% c(1, 2), df$ATBRGL7, NA)) # Keep only Strongly disagree (1) and Neither agree nor disagree (2)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'Strongly disagree' and 'Neither agree nor disagree' in ATBGRL1
df_filtered_ATBRGL7<- df[df$ATBRGL7%in% c(1, 2), ]

# Remove rows with NA in the variables of interest
df_filtered_ATBRGL7<- na.omit(df_filtered_ATBRGL7)

# Build the logistic regression model
model <- glm(ATBRGL7~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_ATBRGL7, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

#Model with only GENRE and AGE
alternative_model1 <- glm(ATBRGL7~ GENRE + AGE, data = df_filtered_ATBRGL7, family = binomial())

#Model with only GENRE and NIVSCOL
alternative_model2 <- glm(ATBRGL7~ GENRE + NIVSCOL, data = df_filtered_ATBRGL7, family = binomial())

#Model with only AGE and NIVSCOL
alternative_model3 <- glm(ATBRGL7~ AGE + NIVSCOL, data = df_filtered_ATBRGL7, family = binomial())

#Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(ATBRGL7~ GENRE + AGE + NIVSCOL, data = df_filtered_ATBRGL7, family = binomial())

#Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(ATBRGL7~ GENRE + HEALTH_SCIENCE, data = df_filtered_ATBRGL7, family = binomial())

#Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(ATBRGL7~ AGE + HEALTH_SCIENCE, data = df_filtered_ATBRGL7, family = binomial())

#Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(ATBRGL7~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_ATBRGL7, family = binomial())

#Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3,
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)
print(aic_values)

#### ATBRGL8#### 

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$ATBRGL8<- as.factor(ifelse(df$ATBRGL8%in% c(1, 2), df$ATBRGL8, NA)) # Keep only Strongly disagree (1) and Neither agree nor disagree (2)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'Strongly disagree' and 'Neither agree nor disagree' in ATBGRL1
df_filtered_ATBRGL8<- df[df$ATBRGL8%in% c(1, 2), ]

# Remove rows with NA in the variables of interest
df_filtered_ATBRGL8<- na.omit(df_filtered_ATBRGL8)

# Build the logistic regression model
model <- glm(ATBRGL8~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_ATBRGL8, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

#Model with only GENRE and AGE
alternative_model1 <- glm(ATBRGL8~ GENRE + AGE, data = df_filtered_ATBRGL8, family = binomial())

#Model with only GENRE and NIVSCOL
alternative_model2 <- glm(ATBRGL8~ GENRE + NIVSCOL, data = df_filtered_ATBRGL8, family = binomial())

#Model with only AGE and NIVSCOL
alternative_model3 <- glm(ATBRGL8~ AGE + NIVSCOL, data = df_filtered_ATBRGL8, family = binomial())

#Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(ATBRGL8~ GENRE + AGE + NIVSCOL, data = df_filtered_ATBRGL8, family = binomial())

#Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(ATBRGL8~ GENRE + HEALTH_SCIENCE, data = df_filtered_ATBRGL8, family = binomial())

#Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(ATBRGL8~ AGE + HEALTH_SCIENCE, data = df_filtered_ATBRGL8, family = binomial())

#Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(ATBRGL8~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_ATBRGL8, family = binomial())

#Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3,
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)
print(aic_values)

#### RESDIM1 #### 

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$RESDIM1<- as.factor(ifelse(df$RESDIM1%in% c(1, 2), df$RESDIM1, NA)) # Keep only Strongly disagree (1) and Neither agree nor disagree (2)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'Strongly disagree' and 'Neither agree nor disagree' in ATBGRL1
df_filtered_RESDIM1<- df[df$RESDIM1%in% c(1, 2), ]

# Remove rows with NA in the variables of interest
df_filtered_RESDIM1<- na.omit(df_filtered_RESDIM1)

# Build the logistic regression model
model <- glm(RESDIM1~ AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESDIM1, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

#Model with only AGE and NIVSCOL
alternative_model1 <- glm(RESDIM1~ AGE + NIVSCOL, data = df_filtered_RESDIM1, family = binomial())

#Model with AGE and HEALTH_SCIENCE
alternative_model2 <- glm(RESDIM1~ AGE + HEALTH_SCIENCE, data = df_filtered_RESDIM1, family = binomial())

#Model with NIVSCOL and HEALTH_SCIENCE
alternative_model3 <- glm(RESDIM1~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESDIM1, family = binomial())

#Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3)
print(aic_values)

#### RESDIM2 #### 

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$RESDIM2<- as.factor(ifelse(df$RESDIM2%in% c(3, 2), df$RESDIM2, NA)) # Keep only Strongly agree (1) and Neither agree nor disagree (2)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'Strongly disagree' and 'Neither agree nor disagree' in ATBGRL1
df_filtered_RESDIM2<- df[df$RESDIM2%in% c(3, 2), ]

# Remove rows with NA in the variables of interest
df_filtered_RESDIM2<- na.omit(df_filtered_RESDIM2)

# Build the logistic regression model
model <- glm(RESDIM2~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESDIM2, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

#Model with only GENRE and AGE
alternative_model1 <- glm(RESDIM2~ GENRE + AGE, data = df_filtered_RESDIM2, family = binomial())

#Model with only GENRE and NIVSCOL
alternative_model2 <- glm(RESDIM2~ GENRE + NIVSCOL, data = df_filtered_RESDIM2, family = binomial())

#Model with only AGE and NIVSCOL
alternative_model3 <- glm(RESDIM2~ AGE + NIVSCOL, data = df_filtered_RESDIM2, family = binomial())

#Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(RESDIM2~ GENRE + AGE + NIVSCOL, data = df_filtered_RESDIM2, family = binomial())

#Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(RESDIM2~ GENRE + HEALTH_SCIENCE, data = df_filtered_RESDIM2, family = binomial())

#Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(RESDIM2~ AGE + HEALTH_SCIENCE, data = df_filtered_RESDIM2, family = binomial())

#Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(RESDIM2~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESDIM2, family = binomial())

#Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3,
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)
print(aic_values) 

#### RESDIM3 #### 

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$RESDIM3<- as.factor(ifelse(df$RESDIM3%in% c(1, 2), df$RESDIM3, NA)) # Keep only Strongly disagree (1) and Neither agree nor disagree (2)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'Strongly disagree' and 'Neither agree nor disagree' in ATBGRL1
df_filtered_RESDIM3<- df[df$RESDIM3%in% c(1, 2), ]

# Remove rows with NA in the variables of interest
df_filtered_RESDIM3<- na.omit(df_filtered_RESDIM3)

# Build the logistic regression model
model <- glm(RESDIM3~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESDIM3, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

#Model with only GENRE and AGE
alternative_model1 <- glm(RESDIM3~ GENRE + AGE, data = df_filtered_RESDIM3, family = binomial())

#Model with only GENRE and NIVSCOL
alternative_model2 <- glm(RESDIM3~ GENRE + NIVSCOL, data = df_filtered_RESDIM3, family = binomial())

#Model with only AGE and NIVSCOL
alternative_model3 <- glm(RESDIM3~ AGE + NIVSCOL, data = df_filtered_RESDIM3, family = binomial())

#Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(RESDIM3~ GENRE + AGE + NIVSCOL, data = df_filtered_RESDIM3, family = binomial())

#Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(RESDIM3~ GENRE + HEALTH_SCIENCE, data = df_filtered_RESDIM3, family = binomial())

#Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(RESDIM3~ AGE + HEALTH_SCIENCE, data = df_filtered_RESDIM3, family = binomial())

#Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(RESDIM3~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESDIM3, family = binomial())

#Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3,
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)
print(aic_values)

#### RESDIM4 #### 

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$RESDIM4<- as.factor(ifelse(df$RESDIM4%in% c(3, 2), df$RESDIM4, NA)) # Keep only Strongly agree (3) and Neither agree nor disagree (2)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'Strongly disagree' and 'Neither agree nor disagree' in ATBGRL1
df_filtered_RESDIM4<- df[df$RESDIM4%in% c(3, 2), ]

# Remove rows with NA in the variables of interest
df_filtered_RESDIM4<- na.omit(df_filtered_RESDIM4)

# Build the logistic regression model
model <- glm(RESDIM4~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESDIM4, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

#Model with only GENRE and AGE
alternative_model1 <- glm(RESDIM4~ GENRE + AGE, data = df_filtered_RESDIM4, family = binomial())

#Model with only GENRE and NIVSCOL
alternative_model2 <- glm(RESDIM4~ GENRE + NIVSCOL, data = df_filtered_RESDIM4, family = binomial())

#Model with only AGE and NIVSCOL
alternative_model3 <- glm(RESDIM4~ AGE + NIVSCOL, data = df_filtered_RESDIM4, family = binomial())

#Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(RESDIM4~ GENRE + AGE + NIVSCOL, data = df_filtered_RESDIM4, family = binomial())

#Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(RESDIM4~ GENRE + HEALTH_SCIENCE, data = df_filtered_RESDIM4, family = binomial())

#Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(RESDIM4~ AGE + HEALTH_SCIENCE, data = df_filtered_RESDIM4, family = binomial())

#Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(RESDIM4~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESDIM4, family = binomial())

#Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3,
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)
print(aic_values)

#### RESDIM5 #### 

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$RESDIM5<- as.factor(ifelse(df$RESDIM5%in% c(1, 2), df$RESDIM5, NA)) # Keep only Strongly disagree (1) and Neither agree nor disagree (2)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'Strongly disagree' and 'Neither agree nor disagree' in ATBGRL1
df_filtered_RESDIM5<- df[df$RESDIM5%in% c(1, 2), ]

# Remove rows with NA in the variables of interest
df_filtered_RESDIM5<- na.omit(df_filtered_RESDIM5)

# Build the logistic regression model
model <- glm(RESDIM5~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESDIM5, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

#Model with only GENRE and AGE
alternative_model1 <- glm(RESDIM5~ GENRE + AGE, data = df_filtered_RESDIM5, family = binomial())

#Model with only GENRE and NIVSCOL
alternative_model2 <- glm(RESDIM5~ GENRE + NIVSCOL, data = df_filtered_RESDIM5, family = binomial())

#Model with only AGE and NIVSCOL
alternative_model3 <- glm(RESDIM5~ AGE + NIVSCOL, data = df_filtered_RESDIM5, family = binomial())

#Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(RESDIM5~ GENRE + AGE + NIVSCOL, data = df_filtered_RESDIM5, family = binomial())

#Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(RESDIM5~ GENRE + HEALTH_SCIENCE, data = df_filtered_RESDIM5, family = binomial())

#Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(RESDIM5~ AGE + HEALTH_SCIENCE, data = df_filtered_RESDIM5, family = binomial())

#Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(RESDIM5~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESDIM5, family = binomial())

#Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3,
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)
print(aic_values)

#### RESDIM6 #### 

# Load database
Database_simplified <- read_excel("C:/Database_simplified.xlsx")
df <- Database_simplified

# Prepare the variables
df$RESDIM6<- as.factor(ifelse(df$RESDIM6%in% c(1, 2), df$RESDIM6, NA)) # Keep only Strongly disagree (1) and Neither agree nor disagree (2)
df$GENRE <- as.factor(ifelse(df$GENRE %in% c(0, 1), df$GENRE, NA)) # Keep only Female (0) and Male (1)
df$AGE <- as.factor(ifelse(df$AGE %in% c(1, 2), "18-34", ifelse(df$AGE %in% c(3, 4, 5, 6), "35+", NA)))
df$NIVSCOL <- as.factor(ifelse(df$NIVSCOL %in% c(7, 8), "Higher Education", "Other"))
df$HEALTH_SCIENCE <- ifelse(Database_simplified$PROF11 == 0 | Database_simplified$PROF12 == 0, 0, 1)

# Filter for 'Strongly disagree' and 'Neither agree nor disagree' in ATBGRL1
df_filtered_RESDIM6<- df[df$RESDIM6%in% c(1, 2), ]

# Remove rows with NA in the variables of interest
df_filtered_RESDIM6<- na.omit(df_filtered_RESDIM6)

# Build the logistic regression model
model <- glm(RESDIM6~ GENRE + AGE + NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESDIM6, family = binomial())

# Check the results
summary(model)

# To obtain Odds Ratios and confidence intervals
exp(cbind(OddsRatio = coef(model), confint(model)))

# Check for multicollinearity with VIF
vif_model <- vif(model)
print(vif_model)

# Fit alternative models for AIC comparison

#Model with only GENRE and AGE
alternative_model1 <- glm(RESDIM6~ GENRE + AGE, data = df_filtered_RESDIM6, family = binomial())

#Model with only GENRE and NIVSCOL
alternative_model2 <- glm(RESDIM6~ GENRE + NIVSCOL, data = df_filtered_RESDIM6, family = binomial())

#Model with only AGE and NIVSCOL
alternative_model3 <- glm(RESDIM6~ AGE + NIVSCOL, data = df_filtered_RESDIM6, family = binomial())

#Model with GENRE, AGE, and NIVSCOL
alternative_model4 <- glm(RESDIM6~ GENRE + AGE + NIVSCOL, data = df_filtered_RESDIM6, family = binomial())

#Model with GENRE and HEALTH_SCIENCE
alternative_model5 <- glm(RESDIM6~ GENRE + HEALTH_SCIENCE, data = df_filtered_RESDIM6, family = binomial())

#Model with AGE and HEALTH_SCIENCE
alternative_model6 <- glm(RESDIM6~ AGE + HEALTH_SCIENCE, data = df_filtered_RESDIM6, family = binomial())

#Model with NIVSCOL and HEALTH_SCIENCE
alternative_model7 <- glm(RESDIM6~ NIVSCOL + HEALTH_SCIENCE, data = df_filtered_RESDIM6, family = binomial())

#Compare AIC of all models
aic_values <- AIC(model, alternative_model1, alternative_model2, alternative_model3,
                  alternative_model4, alternative_model5, alternative_model6, alternative_model7)
print(aic_values)