A6q4-2

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)

data <- read_excel("C:/Users/kvpra/Documents/spring 2026/rlaanguage/A6Q4-2.xlsx")
colnames(data) <- c("Exercise", "Weight")

data %>%
  group_by(Exercise) %>%
  summarise(
    Mean = mean(Weight, na.rm = TRUE),
    Median = median(Weight, na.rm = TRUE),
    SD = sd(Weight, na.rm = TRUE),
    N = n()
  )

## # A tibble: 2 × 5
##   Exercise  Mean Median    SD     N
##   <chr>    <dbl>  <dbl> <dbl> <int>
## 1 lift     120.   116.   53.3    25
## 2 nolift    33.0   40.8  56.7    25

hist(data$Weight[data$Exercise == "lift"],
     main = "Histogram of Lift Weight",
     xlab = "Weight (kg)",
     ylab = "Frequency",
     col = "lightblue",
     border = "black",
     breaks = 10)

hist(data$Weight[data$Exercise == "nolift"],
     main = "Histogram of No Lift Weight",
     xlab = "Weight (kg)",
     ylab = "Frequency",
     col = "lightgreen",
     breaks = 10)

#Group 1: No Lift
#The first variable looks abnormally distributed.
#The data is negatively skewed.
#The data does not have a proper bell curve.

#Group 2: Lift
#The second variable looks abnormally distributed.
#The data is positively skewed.
#The data does not have a proper bell curve.

ggboxplot(data, x = "Exercise", y = "Weight",
          color = "Exercise",
          palette = "jco",
          add = "jitter")

#Boxplot 1: No Lift
#There are dots outside the boxplot.
#The dots are not close to the whiskers.
#The dots are very far away from the whiskers.
#The outliers are not balanced.
#Based on these findings, the boxplot is not normal.

#Boxplot 2: Lift
#There are dots outside the boxplot.
#The dots are not close to the whiskers.
#The dots are very far away from the whiskers.
#The outliers are not balanced.
#Based on these findings, the boxplot is not normal.

shapiro.test(data$Weight[data$Exercise == "lift"])

## 
##  Shapiro-Wilk normality test
## 
## data:  data$Weight[data$Exercise == "lift"]
## W = 0.78786, p-value = 0.0001436

shapiro.test(data$Weight[data$Exercise == "nolift"])

## 
##  Shapiro-Wilk normality test
## 
## data:  data$Weight[data$Exercise == "nolift"]
## W = 0.70002, p-value = 7.294e-06

#Group 1: Lift
#The first group is abnormally distributed, (p < .001).

#Group 2: No Lift
#The second group is abnormally distributed, (p < .001).

# Final Normality Decision

# Lift group:
# Histogram = abnormal
# Boxplot = abnormal
# Shapiro-Wilk = abnormal
# Final decision: The data is abnormally distributed.

# No Lift group:
# Histogram = abnormal
# Boxplot = abnormal
# Shapiro-Wilk = abnormal
# Final decision: The data is abnormally distributed.

wilcox.test(Weight ~ Exercise, data = data)

## 
##  Wilcoxon rank sum exact test
## 
## data:  Weight by Exercise
## W = 603, p-value = 7.132e-11
## alternative hypothesis: true location shift is not equal to 0

mw_effect <- cliff.delta(Weight ~ Exercise, data = data)
print(mw_effect)

## 
## Cliff's Delta
## 
## delta estimate: 0.9296 (large)
## 95 percent confidence interval:
##     lower     upper 
## 0.7993841 0.9764036

# A Mann-Whitney U test was conducted to determine if there was a difference in body weight between participants who lift weights and those who do not.
# Lift scores (Mdn = 116.00) were significantly different from No Lift scores (Mdn = 40.84), U = 603.00, p < .001.
# The effect size was large, Cliff's Delta = .93.