Scenario 6.2 Study Hours URL:http://rpubs.com/pmohammed/1399071

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)

Dataset6_2 <- read_excel("C:/Users/Mrlaz/Downloads/Dataset6.2.xlsx")

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
hist(Dataset6_2$Study_Hours[Dataset6_2$Work_Status=="Works"],
     main="Works", col="lightblue")

hist(Dataset6_2$Study_Hours[Dataset6_2$Work_Status=="Does_Not_Work"],
     main="Does Not Work", col="lightgreen")

ggboxplot(Dataset6_2, x="Work_Status", y="Study_Hours",
          color="Work_Status", add="jitter")

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
t.test(Study_Hours ~ Work_Status, data=Dataset6_2, var.equal=TRUE)
## 
##  Two Sample t-test
## 
## data:  Study_Hours by Work_Status
## t = 2.0306, df = 58, p-value = 0.04688
## alternative hypothesis: true difference in means between group Does_Not_Work and group Works is not equal to 0
## 95 percent confidence interval:
##  0.04572065 6.37400708
## sample estimates:
## mean in group Does_Not_Work         mean in group Works 
##                    9.616468                    6.406604
wilcox.test(Study_Hours ~ Work_Status, data=Dataset6_2)
## 
##  Wilcoxon rank sum exact test
## 
## data:  Study_Hours by Work_Status
## W = 569, p-value = 0.07973
## alternative hypothesis: true location shift is not equal to 0
cohens_d(Study_Hours ~ Work_Status, data=Dataset6_2, pooled_sd=TRUE)
## Cohen's d |       95% CI
## ------------------------
## 0.52      | [0.01, 1.04]
## 
## - Estimated using pooled SD.

Normality Works p = 0.131 → normal Does_Not_Work p = 0.0004 → NOT normal Not both normal → Mann-Whitney U test Medians Works ≈ 5.70 hrs Does_Not_Work ≈ 8.40 hrs Significance p ≈ .047 → significant Students who work (Mdn = 5.70) were significantly different from students who do not work (Mdn = 8.40) in weekly study hours, p = .047.