test 2

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

## 
## Attaching package: 'effectsize'

## The following object is masked from 'package:rcompanion':
## 
##     phi

library(effsize)
Dataset6_2 <- read_excel("C:/Users/user/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

# Histograms for Each Group
hist(Dataset6_2$Study_Hours[Dataset6_2$Work_Status == "Works"],
     main = "Histogram of works",
     xlab = "value",
     ylab = "Frequency",
     col = "lightblue",
     border = "black",
     breaks = 10)

hist(Dataset6_2$Study_Hours[Dataset6_2$Work_Status == "Does_Not_Work"],
     main = "Histogram of Does_Not_Work",
     xlab = "value",
     ylab = "Frequency",
     col = "lightgreen",
     border = "black",
     breaks = 10)

#For the Does_Not_Work  histogram, the data appears negatively skewed.
#It is difficult to state the exact kurtosis, but it appears abnormal.
#For the works histogram, the data appears symmetrical (normal).
#The kurtosis also appears bell-shaped (normal).


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

#the work  boxplot appears normal. There are no dots past the whiskers.

#The does not work boxplot appears abnormal.
#There are several dots past the whiskers.
#Although some are very close to the whiskers, some are arguably far away.

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

# p < .05 (less than .05), the data was NOT normal.

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

# p > .05 (greater than .05), this means the results were NOT significant
#student who do not work ((Mdn = 8.54) was not significantly different from student who work  (Mdn = 5.64), U =569, p = .080.
# No effect size .