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(readxl)
library(ggpubr)

## Loading required package: ggplot2

CardioWeight <- read_excel("C:/Users/tawan/OneDrive - Saint Louis University/AA 5221/Assignment 6/A6Q3.xlsx")
View(CardioWeight)

CardioWeight %>%
  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

hist(CardioWeight$Weight[CardioWeight$Exercise == "nocardio"],
     breaks = 15,
     main = "Histogram of Weight Non Cardio Paticipants",
     xlab = "No Cardio",
     col = "skyblue",
     border = "white")

hist(CardioWeight$Weight[CardioWeight$Exercise == "cardio"],
     breaks = 15,
     main = "Histogram of Weight Cardio Exercising Participants",
     xlab = "Cardio",
     col = "firebrick",
     border = "white")

#Data for nocardio appears normally distributed.
#Data for cardio appears normally distributed.

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

# The noocardio boxplot does have  outliers.
# The cardio boxplot does have  outliers.

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

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

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

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

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

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

cohens_d_result <- cohens_d(Weight ~ Exercise, data = CardioWeight, 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 nocardio and cardio.
#nocardio scores (M = 70.8, SD = 7.35) were significantly different from cardio (M = 74.7, SD = 7.57), t(48) = 1.86, p > .05.
#The effect size was medium, Cohen's d = .52.