============================== DATASET B2: StudentType and PetOwnership ==============================

#Open the installed packages

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

#Import & Name Dataset

DatasetB2 <- read_excel("/Users/atharvapitke/Documents/Analytics/Assignment 5/DatasetB2.xlsx")

#Create a Contingency Table

tab <- table(DatasetB2$StudentType, DatasetB2$PetOwnership)
tab
##                
##                 No Yes
##   Domestic      27  25
##   International 23  25

#Create Bar Charts

ggplot(DatasetB2, aes(x = StudentType, fill = PetOwnership)) +
  geom_bar(position = "dodge") +                 
  labs(
    x = "StudentType",
    y = "Frequency",
    title = "PetOwnership by StudentType"
  ) +
  theme(
    text = element_text(size = 14),
    axis.title = element_text(size = 14),
    axis.text = element_text(size = 14),
    plot.title = element_text(size = 14),
    legend.position = "none"                 
  )

#Conduct the Chi-Square Test of Independence

chisq.test(tab)
## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  tab
## X-squared = 0.040064, df = 1, p-value = 0.8414

#Results

The Chi-Square Test of Independence indicated there was a weak association between StudentType and PetOwnership, χ²(1) = 0.040064, p = 0.8414. The Cramer’s V (Effect Size) was not calculated because the p-value was not statistically significant.