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)

A6Q3_Sheet1_ <- read_excel(
  "C:/Users/hp/Desktop/digital Forensics/AA 5221/A6Q3(Sheet1).xlsx"
)

View(A6Q3_Sheet1_)
unique(A6Q3_Sheet1_$Exercise)  # Check the exact group names

## [1] "nocardio" "cardio"

# Descriptive statistics
A6Q3_Sheet1_ %>%
  group_by(Exercise) %>%
  summarise(
    Mean = mean(Weight, na.rm = TRUE),
    Median = median(Weight, na.rm = TRUE),
    SD = sd(Weight, na.rm = TRUE),
    N = sum(!is.na(Weight)),
    .groups = "drop"
  )

## # A tibble: 2 × 5
##   Exercise  Mean Median    SD     N
##   <chr>    <dbl>  <dbl> <dbl> <int>
## 1 cardio    74.7   73.3  7.57    25
## 2 nocardio  70.8   69.5  7.35    25

hist(A6Q3_Sheet1_$Weight[A6Q3_Sheet1_$Exercise == "cardio"],
     breaks = 15,
     col = "skyblue",
     border = "white")

hist(A6Q3_Sheet1_$Weight[A6Q3_Sheet1_$Exercise == "nocardio"],
     breaks = 15,
     col = "firebrick",
     border = "white")

#Data for Weight of nocardio appears normally distributed.
#Data for weight of cardio appears normally distributed.

ggboxplot(A6Q3_Sheet1_, x = "Exercise", y = "Weight",
          color = "Exercise",
          palette = "jco",
          add = "jitter")

# The Cardio boxplot does not have outliers.
# The No-Cardio boxplot has outliers.

shapiro.test(A6Q3_Sheet1_$Weight[A6Q3_Sheet1_$Exercise == "cardio"])

## 
##  Shapiro-Wilk normality test
## 
## data:  A6Q3_Sheet1_$Weight[A6Q3_Sheet1_$Exercise == "cardio"]
## W = 0.96745, p-value = 0.5812

shapiro.test(A6Q3_Sheet1_$Weight[A6Q3_Sheet1_$Exercise == "nocardio"])

## 
##  Shapiro-Wilk normality test
## 
## data:  A6Q3_Sheet1_$Weight[A6Q3_Sheet1_$Exercise == "nocardio"]
## W = 0.97686, p-value = 0.8166

#The cardio group is normally distributed, (p > .05).
#The nocardio group is normally distributed, (p > .05).

t.test(Weight ~ Exercise, data = A6Q3_Sheet1_, var.equal = TRUE)

## 
##  Two Sample t-test
## 
## data:  Weight by Exercise
## t = 1.8552, df = 48, p-value = 0.06971
## alternative hypothesis: true difference in means between group cardio and group nocardio is not equal to 0
## 95 percent confidence interval:
##  -0.3280454  8.1605622
## sample estimates:
##   mean in group cardio mean in group nocardio 
##               74.73336               70.81710

#Two Sample t-test

cohens_d_result <- cohens_d(Weight ~ Exercise, data = A6Q3_Sheet1_, pooled_sd = TRUE)
print(cohens_d_result)

## Cohen's d |        95% CI
## -------------------------
## 0.52      | [-0.04, 1.09]
## 
## - Estimated using pooled SD.

# An Independent T-Test was conducted to determine if there was a difference in Weight between cardio and nocardio.
# Cardio scores (M = 74.7, SD = 7.57) were not significantly different from nocardio scores (M = 70.8, SD = 7.35), t(48) = 1.86, p = .070.
# The effect size was medium, Cohen's d = 0.52.