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("/Users/asfia/Desktop/Dataset6.2.xlsx")
head(Dataset6.2)
## # A tibble: 6 × 2
## Work_Status Study_Hours
## <chr> <dbl>
## 1 Works 3.57
## 2 Works 13.2
## 3 Works 0.577
## 4 Works 6.65
## 5 Works 17.3
## 6 Works 8.47
str(Dataset6.2)
## tibble [60 × 2] (S3: tbl_df/tbl/data.frame)
## $ Work_Status: chr [1:60] "Works" "Works" "Works" "Works" ...
## $ Study_Hours: num [1:60] 3.568 13.247 0.577 6.65 17.344 ...
Dataset6.2 %>%
group_by(Work_Status) %>%
summarise(
Mean = mean(Study_Hours),
Median = median(Study_Hours),
SD = sd(Study_Hours),
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 == "Does_Not_Work"],
main = "Histogram of Study Hours - Non-Working Students",
xlab = "Study Hours per Week",
ylab = "Frequency",
col = "lightgreen",
border = "darkgreen",
breaks = 10)
#### Skewness: Positively Skewed ,“,”Kurtosis: It is difficult to state
the exact kurtosis, but it appears abnormal
hist(Dataset6.2$Study_Hours[Dataset6.2$Work_Status == "Works"],
main = "Histogram of Study Hours - Working Students",
xlab = "Study Hours per Week",
ylab = "Frequency",
col = "lightblue",
border = "blue",
breaks = 10)
#### Skewness: Positively Skewed ,“,”Kurtosis: It is difficult to state
the exact kurtosis, but it appears abnormal
ggboxplot(Dataset6.2, x = "Work_Status", y = "Study_Hours",
color = "Work_Status",
palette = c("blue", "green"),
add = "jitter",
title = "Study Hours by Work Status",
xlab = "Work Status",
ylab = "Study Hours per Week")
#### For Working group: the data looks somewhat normal with only one
outlier and For Non-Working group: the data looks abnormal with multiple
outliers and unevely distributed so Based on Reports we use the
Mann-Whitney U 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
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