Chi-Square

library(readxl)
library(ggplot2)

DatasetA <- read_excel("C:/Users/JT/Downloads/DatasetA2.xlsx")
DatasetB <- read_excel("C:/Users/JT/Downloads/DatasetB2.xlsx")

table(DatasetA$FavoriteDrink)

## 
## Coffee   Soda    Tea  Water 
##     26     29     28     17

ggplot(DatasetA, aes(x = FavoriteDrink, fill = FavoriteDrink)) +
  geom_bar() +
  labs(
    x = "Variable Name",
    y = "Frequency",
    title = "Distribution of Variable Name"
  ) +
  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"             
  )

observed <- c(26, 29, 28 , 17) 
expected <- c(0.25, 0.25, 0.25 , 0.25)
chisq.test(x = observed, p = expected)

## 
##  Chi-squared test for given probabilities
## 
## data:  observed
## X-squared = 3.6, df = 3, p-value = 0.308

A chi-square goodness-of-fit test indicated that the observed frequencies were different, χ²(3) = 3.6, p = 0.308.

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

tab <- table(DatasetB$StudentType, DatasetB$PetOwnership)

ggplot(DatasetB, aes(x = StudentType, fill = PetOwnership)) +
  geom_bar(position = "dodge") +               
  labs(
    x = "Variable A",
    y = "Frequency",
    title = "Variable B by Variable A"
  ) +
  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"                 
  )

chisq.test(tab)

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

The Chi-Square Test of Independence indicated there was not a significant association between StudentType and PetOwnership, χ²(1) = 0.040064 , p = 0.8414. The p value was not statistically significant so we cannot calculate the effect size.