library(readxl)
library(ggpubr)

## Loading required package: ggplot2

library(effsize)
library(rstatix)

## 
## Attaching package: 'rstatix'

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

A6Q1 <- read_excel("C:/Users/tmd97/Downloads/A6Q1.xlsx")
View(A6Q1)
Before <- A6Q1$Before
After <- A6Q1$After

Differences <- After - Before
mean(Before, na.rm = TRUE)

## [1] 76.13299

median(Before, na.rm = TRUE)

## [1] 75.95988

sd(Before, na.rm = TRUE)

## [1] 7.781323

mean(After, na.rm = TRUE)

## [1] 71.58994

median(After, na.rm = TRUE)

## [1] 70.88045

sd(After, na.rm = TRUE)

## [1] 6.639509

hist(Differences,
     breaks = 15,
     col = "blue",
     border = "white")

# Data for the difference scores appears normally distributed.
# I added the histogram when correcting this assignment because when I originally completed the assignment, I was unable to generate the histogram because R returned an error indicating that the values were too far apart.
boxplot(Differences,
        main = "Distribution of Score Differences (After - Before)",
        ylab = "Difference in Scores",
        col = "blue",
        border = "darkblue")

# The difference scores boxplot does not have outliers.
# I added the boxplot when correcting this assignment because when I originally completed this assignment, I was unable to generate the boxplot because R returned an error indicating that the values were too far apart.
shapiro.test(Differences)

## 
##  Shapiro-Wilk normality test
## 
## data:  Differences
## W = 0.94757, p-value = 0.3318

#Shapiro-Wilk Difference Scores
#The data is normally distributed, (p = .33).
t.test(Before, After, paired = TRUE, na.action = na.omit)

## 
##  Paired t-test
## 
## data:  Before and After
## t = 1.902, df = 19, p-value = 0.07245
## alternative hypothesis: true mean difference is not equal to 0
## 95 percent confidence interval:
##  -0.4563808  9.5424763
## sample estimates:
## mean difference 
##        4.543048

cohen.d(Before, After, paired = TRUE)

## 
## Cohen's d
## 
## d estimate: 0.6284306 (medium)
## 95 percent confidence interval:
##      lower      upper 
## -0.1035207  1.3603820

#A Dependent T-Test was conducted to determine if there was a difference in weight between Before versus After low calorie diet.
#I added "low calorie diet" to the previous line. I had previously forgot to add that information and had left as "difference in weight between before and after".
#Before scores (M = 76.13, SD = 7.78) were significantly different from After scores (M = 71.59, SD = 6.64), (t(19) = 1.90, p < .05)
#I corrected p > .05 to p < .05 because I was looking the wrong p-value, specifically I based my answer on the Shapiro-Wilk p-value which is .33. Which is why I viewed it as not significantly different.
#The effect size was Large, Cohen's d = .63.
#I corrected the size from medium to large and rounded the Cohen's d up one. I originally mixed the medium and large size effects up I thought that the medium effect was 0.80 and the large effect was 1.20. I had originally wrote the Cohen's d = .628 instead of rounding because the template showed 3 decimals. But know I know I should just round up regardless.