library(readxl)
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)
library(ggpubr)

## Loading required package: ggplot2

library(rstatix)

## 
## Attaching package: 'rstatix'

## The following objects are masked from 'package:effectsize':
## 
##     cohens_d, eta_squared, omega_squared

## The following object is masked from 'package:stats':
## 
##     filter

A6Q3 <- read_excel("//apporto.com/dfs/SLU/Users/brentgallagher_slu/Desktop/A6Q3.xlsx")
A6Q3 %>%
  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 cardio    74.7   73.3  7.57    25
## 2 nocardio  70.8   69.5  7.35    25

# Cardio - Mean 74.7, Median 73.3, SD 7.57
# No Cardio - Mean 70.8, Median 69.6, SD 7.35

hist(A6Q3$Weight[A6Q3$Exercise == 
"cardio"],
breaks = 15,
col = "skyblue",
border = "white")

hist(A6Q3$Weight[A6Q3$Exercise ==
"nocardio"],
breaks = 15,
col = "firebrick",
border = "white")

# Data for group one appears abnormally distributed.
# Data for group two appears abnormally distributed.

ggboxplot(A6Q3, x ="Exercise", y = "Weight",
          color = "Exercise",
          palette = "jco",
          add = "jitter")

# Group one does have outliers.
# Group two does have outliers.

shapiro.test(A6Q3$Weight[A6Q3$Exercise == "cardio"])

## 
##  Shapiro-Wilk normality test
## 
## data:  A6Q3$Weight[A6Q3$Exercise == "cardio"]
## W = 0.96745, p-value = 0.5812

shapiro.test(A6Q3$Weight[A6Q3$Exercise == "nocardio"])

## 
##  Shapiro-Wilk normality test
## 
## data:  A6Q3$Weight[A6Q3$Exercise == "nocardio"]
## W = 0.97686, p-value = 0.8166

# The first group is normally distributed, (p > .05) p-value = 0.58
# The second group is normally distributed, (p > .05) p-value = 0.82

t.test(Weight ~ Exercise,
data = A6Q3, 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

# Mean Cardio 74.73 
# Mean No Cardio 70.81

cohens_d_result <- effectsize::cohens_d(
  Weight ~ Exercise,
  data = A6Q3,
  pooled_sd = TRUE
)

print(cohens_d_result)

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

# Cohen's d = 0.52
# An Independent T-test was conducted to determine if there was a difference in Outcome Varibale between Group 1 and Group 2.
# Group 1 scores (M = 73.30, SD= 7.57) were not significatly different from Group 2 scores (M = 69.60, SD = 7.35).
# The effect size was medium, Cohen's d = 0.52.