# DEPENDENT T-TEST & WILCOXON SIGN RANK
# Used to test if there is a difference between Before scores and After scores (comparing the means).
# NULL HYPOTHESIS (H0)
# The null hypothesis is ALWAYS used.
# There is no difference between the Before and After scores.
# ALTERNATE HYPOTHESIS (H1)
# Choose ONE of the three options below (based on your research scenario):
# 3) DIRECTIONAL ALTERNATE HYPOTHESIS TWO: PostCampaignSales are higher than PreCampaignSales.
# IMPORT EXCEL FILE
# Purpose: Import your Excel dataset into R to conduct analyses.
# INSTALL REQUIRED PACKAGE
# If never installed, remove the hashtag before the install code.
# If previously installed, leave the hashtag in front of the code.
# install.packages("readxl")
# LOAD THE PACKAGE
# Always reload the package you want to use.
library(readxl)
## Warning: package 'readxl' was built under R version 4.5.1
# IMPORT EXCEL FILE INTO R STUDIO
# Download the Excel file from One Drive and save it to your desktop.
# Right-click the Excel file and click “Copy as path” from the menu.
# In RStudio, replace the example path below with your actual path.
# Replace backslashes \ with forward slashes / or double them //:
# ✘ WRONG "C:\Users\Joseph\Desktop\mydata.xlsx"
# ✔ CORRECT "C:/Users/Joseph/Desktop/mydata.xlsx"
# ✔ CORRECT "C:\\Users\\Joseph\\Desktop\\mydata.xlsx"
# Replace "dataset" with the name of your excel data (without the .xlsx)
dataset <- read_excel("C:/Users/User/Downloads/A6R4.xlsx")
A6R4 <- read_excel("C:/Users/User/Downloads/A6R4.xlsx")
# CALCULATE THE DIFFERENCE SCORES
# Calculate the difference between the Before scores versus the after scores.
# RENAME THE VARIABLES
# Replace "dataset" with your dataset name (without .xlsx)
# Replace "pre" with name of your variable for before scores.
# Replace "post" with name of your variable for after scores.
Before <- A6R4$PreCampaignSales
After <- A6R4$PostCampaignSales
Differences <- After - Before
# HISTOGRAM
# Create a histogram for difference scores to visually check skewness and kurtosis.
# CREATE THE HISTOGRAMS
# You do not need to edit this code.
hist(Differences,
main = "Histogram of Difference Scores",
xlab = "Value",
ylab = "Frequency",
col = "blue",
border = "black",
breaks = 20)
# WRITE THE REPORT
# Answer the questions below as a comment within the R script:
# Q1) Is the histograms symmetrical, positively skewed, or negatively skewed?
# The histogram is positively skewed
# Q2) Did the histogram look too flat, too tall, or did it have a proper bell curve?
# The histogram is too tall
# SHAPIRO-WILK TEST
# Check the normality for the difference between the groups.
# CONDUCT SHAPIRO-WILK TEST
# You do not need to edit the code.
shapiro.test(Differences)
##
## Shapiro-Wilk normality test
##
## data: Differences
## W = 0.94747, p-value = 0.01186
# QUESTIONS
# Answer the questions below as a comment within the R script:
# Q1)Was the data normally distributed or abnormally distributed?
# The data is NOT normally didtributed
# If p > 0.05 (P-value is GREATER than .05) this means the data is NORMAL (continue with Dependent t-test).
# If p < 0.05 (P-value is LESS than .05) this means the data is NOT normal (switch to Wilcoxon Sign Rank).
# BOXPLOT
# Check for any outliers impacting the mean.
# CREATE THE BOXPLOT
# You do not need to edit this code
boxplot(Before, After,
names = c("Before", "After"),
main = "Boxplot of Before and After Scores",
col = c("tan", "navy"))
# QUESTIONS
# Answer the questions below as a comment within the R script:
# Q1) Were there any dots outside of the boxplots? These dots represent participants with extreme scores.
# There were a few dots outside of the boxplot
# Q2) If there are outliers, are they are changing the mean so much that the mean no longer accurately represents the average score?
# Q3) Make a decision. If the outliers are extreme, you will need to switch to a Wilcoxon Sign Rank.
# The outliers do not change the mean
# If there are not outliers, or the outliers are not extreme, continue with Dependent t-test.
# DESCRIPTIVE STATISTICS
# Calculate the mean, median, SD, and sample size for each group.
# DESCRIPTIVES FOR BEFORE SCORES
# You do not need to edit this code
mean(Before, na.rm = TRUE)
## [1] 25154.53
median(Before, na.rm = TRUE)
## [1] 24624
sd(Before, na.rm = TRUE)
## [1] 12184.4
length(Before)
## [1] 60
# DESCRIPTIVES FOR AFTER SCORES
# You do not need to edit this code
mean(After, na.rm = TRUE)
## [1] 26873.45
median(After, na.rm = TRUE)
## [1] 25086
sd(After, na.rm = TRUE)
## [1] 14434.37
length(After)
## [1] 60
# WILCOXON SIGN RANK TEST
# Remove the hashtag to use the code
# There are no other edits you need to make to the code.
wilcox.test(Before, After, paired = TRUE)
##
## Wilcoxon signed rank test with continuity correction
##
## data: Before and After
## V = 640, p-value = 0.0433
## alternative hypothesis: true location shift is not equal to 0
# DETERMINE STATISTICAL SIGNIFICANCE
# If results were statistically significant (p < .05), continue to effect size section below.
# If results were NOT statistically significant (p > .05), skip to reporting section below.
# NOTE: Getting results that are not statistically significant does NOT mean you switch to Wilcoxon Sign Rank.
# The Wilcoxon Sign Rank test is only for abnormally distributed data — not based on outcome significance.
# EFFECT SIZE FOR WILCOXON SIGN RANK TEST
# Purpose: Determine how big of a difference there was between the group means.
# INSTALL REQUIRED PACKAGE
# If never installed, remove the hashtag before the install code.
# If previously installed, leave the hashtag in front of the code.
# install.packages("rstatix")
# LOAD THE PACKAGE
# Always reload the package you want to use.
#library(rstatix)
# CALCULATE RANK BISERIAL CORRELATION (EFFECT SIZE)
# You do not need to edit this code, just remove the hashtags
# df_long <- data.frame(
# id = rep(1:length(Before), 2),
# time = rep(c("Before", "After"), each = length(Before)),
# score = c(Before, After)
# )
# WILCOXON SIGN RANK TEST
# Remove the hashtag to use the code
# There are no other edits you need to make to the code.
wilcox.test(Before, After, paired = TRUE)
##
## Wilcoxon signed rank test with continuity correction
##
## data: Before and After
## V = 640, p-value = 0.0433
## alternative hypothesis: true location shift is not equal to 0
# DETERMINE STATISTICAL SIGNIFICANCE
# If results were statistically significant (p < .05), continue to effect size section below.
# If results were NOT statistically significant (p > .05), skip to reporting section below.
# NOTE: Getting results that are not statistically significant does NOT mean you switch to Wilcoxon Sign Rank.
# The Wilcoxon Sign Rank test is only for abnormally distributed data — not based on outcome significance.
# EFFECT SIZE FOR WILCOXON SIGN RANK TEST
# Purpose: Determine how big of a difference there was between the group means.
# INSTALL REQUIRED PACKAGE
# If never installed, remove the hashtag before the install code.
# If previously installed, leave the hashtag in front of the code.
# install.packages("rstatix")
# LOAD THE PACKAGE
# Always reload the package you want to use.
library(rstatix)
## Warning: package 'rstatix' was built under R version 4.5.1
##
## Attaching package: 'rstatix'
## The following object is masked from 'package:stats':
##
## filter
# CALCULATE RANK BISERIAL CORRELATION (EFFECT SIZE)
# You do not need to edit this code, just remove the hashtags
# install.packages("coin")
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 0.261 60 60 small