library(readxl)
library(ggpubr)
## Loading required package: ggplot2
library(dplyr)
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
library(effectsize)
library(effsize)

Working vs Non-Working Students

Import dataset

Dataset6.2<- read_excel("/Users/karim/Desktop/Dataset6.2.xlsx")

Step 4: Descriptive Statistics

Dataset6.2 %>%
  group_by(Work_Status) %>% 
  summarise(
    Mean = mean(Study_Hours, na.rm = TRUE),
    Median = median(Study_Hours, na.rm = TRUE),
    SD = sd(Study_Hours, na.rm = TRUE),
    N = n()
  )
## # A tibble: 2 × 5
##   Work_Status    Mean Median    SD     N
##   <chr>         <dbl>  <dbl> <dbl> <int>
## 1 Does_Not_Work  9.62   8.54  7.45    30
## 2 Works          6.41   5.64  4.41    30

Step 5: Histograms

hist(Dataset6.2$Study_Hours[Dataset6.2$Work_Status == "Works"],
     main = "Works Histogram", xlab = "Study Hours",
     col = "lightblue", border = "black")

hist(Dataset6.2$Study_Hours[Dataset6.2$Work_Status == "Does_Not_Work"],
     main = "Does_Not_Work Histogram", xlab = "Study Hours",
     col = "lightgreen", border = "black")

The histograms appear approximately symmetrical and bell-shaped.

Boxplot

ggboxplot(Dataset6.2, x = "Work_Status", y = "Study_Hours",
          color = "Work_Status",
          palette = "jco",
          add = "jitter")

There were some outliers present.

Step 7: Shapiro-Wilk Test

shapiro.test(Dataset6.2$Study_Hours[Dataset6.2$Work_Status == "Works"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Dataset6.2$Study_Hours[Dataset6.2$Work_Status == "Works"]
## W = 0.94582, p-value = 0.1305
shapiro.test(Dataset6.2$Study_Hours[Dataset6.2$Work_Status == "Does_Not_Work"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Dataset6.2$Study_Hours[Dataset6.2$Work_Status == "Does_Not_Work"]
## W = 0.83909, p-value = 0.0003695

Interpretation: p < .05 = not normal

One group non-normal -> Mann-Whitney U

wilcox_result <- wilcox.test(Study_Hours ~ Work_Status, data = Dataset6.2, exact = FALSE)
wilcox_result
## 
##  Wilcoxon rank sum test with continuity correction
## 
## data:  Study_Hours by Work_Status
## W = 569, p-value = 0.07978
## alternative hypothesis: true location shift is not equal to 0

Cliff’s delta

cliff.delta(Study_Hours ~ Work_Status, data = Dataset6.2)
## 
## Cliff's Delta
## 
## delta estimate: 0.2644444 (small)
## 95 percent confidence interval:
##       lower       upper 
## -0.03422594  0.51975307

The effect size was small (r_rb = 0.26).

Interpretation Mann-Whitney U Result: Working students (Mdn = 5.64) were not significantly different from Non-working students (Mdn = 8.54), U = 331, p = .080.