library(readxl)
library(rcompanion)
library(ggplot2)

StudentData <- read_excel("C:/Users/tawan/OneDrive - Saint Louis University/AA 5221/Assignment 4/A4Q2.xlsx")
table(StudentData$scholarship, StudentData$status)

##    
##     Domestic International
##   0       39           118
##   1      111            32

#data$Gender[data$Gender == "M"] <- "Male"
#data$Gender[data$Gender == "F"] <- "Female"

StudentData$scholarship[StudentData$scholarship == "0"] <- "No scholarship"
StudentData$scholarship[StudentData$scholarship == "1"] <- "Scholarship"

DataCollected <- table(StudentData$scholarship, StudentData$status)
DataCollected

##                 
##                  Domestic International
##   No scholarship       39           118
##   Scholarship         111            32

barplot(DataCollected,
        main = "Student Nationality Scholarships",
        ylab = "Count",
        xlab = "Nationality",
        beside = TRUE,
        col = rainbow(nrow(DataCollected)),
        legend = rownames(DataCollected))

chi_result <- chisq.test(DataCollected)
chi_result

## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  DataCollected
## X-squared = 81.297, df = 1, p-value < 2.2e-16

rcompanion::cramerV(DataCollected)

## Cramer V 
##   0.5272

# A Chi-Square Test of Independence was conducted to determine if there was an association between student nationality and scholarship status.
# The results showed that there was an association between the two variables, χ²(1) = 81.30, p < 0.01.
# The association was large (Cramer's V = .53).