library(rstatix)

## 
## Attaching package: 'rstatix'

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

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)

## 
## Attaching package: 'effectsize'

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

library(effsize)
library(readxl)
library(ggpubr)

## Loading required package: ggplot2

A6Q2 <- read_excel("//apporto.com/dfs/SLU/Users/brentgallagher_slu/Desktop/A6Q2.xlsx")
Before <- A6Q2$Before
After <- A6Q2$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] 57.17874

median(After, na.rm = TRUE)

## [1] 58.36459

sd(After, na.rm = TRUE)

## [1] 14.39364

# Before - mean: 76.13, median: 75.96, sd: 7.81
# After - mean: 57.18, median: 58.36, sd: 14.39
hist(Differences,
     breaks = 15,
     col = "blue",
     border = "white")

# Data for the difference scores appears abnormally distributed.
boxplot(Differences,
        main = "Distribution of Score Differences (After - Before)",
        ylab = "Difference in Scores",
        col = "blue",
        border = "darkblue")

# The difference scores boxplot does have outliers.
shapiro.test(Differences)

## 
##  Shapiro-Wilk normality test
## 
## data:  Differences
## W = 0.89142, p-value = 0.02856

# Shapiro-Wilk Normality test - w = 0.89, p-value = 0.029
# The data is abnormally distributed, (p = .029)
wilcox.test(Before, After, paired = TRUE, na.action = na.omit)

## 
##  Wilcoxon signed rank exact test
## 
## data:  Before and After
## V = 210, p-value = 1.907e-06
## alternative hypothesis: true location shift is not equal to 0

# Data: Before and After, v = 210, p-value = 1.907e-06
# Alternative hypothesis: true location shift is not equal to 0.
df_long <- data.frame(id =
rep(1:length(Before), 2), time
= rep(c("Before", "After"),
each = length(Before)), score
= c (Before, After))

wilcox_effsize(df_long, score
~ time, paired = TRUE)

## # A tibble: 1 × 7
##   .y.   group1 group2 effsize    n1    n2 magnitude
## * <chr> <chr>  <chr>    <dbl> <int> <int> <ord>    
## 1 score After  Before   0.877    20    20 large

# A Wilcoxon Signed-Rank Test was conducted to determine if there was a difference in Outcome Variable before Independent Variable versus after Independent Variable.
# The effect size was large, r = 0.88.