options(repos = c(CRAN = "https://cloud.r-project.org"))
# INDEPENDENT T-TEST & MANN-WHITNEY U TEST
# HYPOTHESIS TESTED:
# Used to test if there is a difference between the means of two groups.
# NULL HYPOTHESIS (H0)
# The null hypothesis below is ALWAYS used.
# There is no difference between the scores of Group A and Group B.
# ALTERNATE HYPOTHESIS (H1)
# Choose ONE of the three options below (based on your research scenario):
# 1) NON-DIRECTIONAL ALTERNATE HYPOTHESIS: There is a difference between the scores of Group A and Group B.
# 2) DIRECTIONAL ALTERNATE HYPOTHESES ONE: Group A has higher scores than Group B.
# 3) DIRECTIONAL ALTERNATE HYPOTHESIS TWO: Group B has higher scores than Group A.
# QUESTION
# What are the null and alternate hypotheses for YOUR research scenario?
# H0: is no difference in Therethe average satisfaction scores between customers served by human agents and those served by the AI chatbot.
# H1:There is a difference in the average satisfaction scores between the two groups.
# IMPORT EXCEL FILE
# INSTALL PACKAGES
# install.packages("readxl")
# LOAD THE PACKAGE
library(readxl)
# IMPORT EXCEL FILE INTO R STUDIO
A6R2 <- read_excel("C:/Users/dubet/OneDrive/Documents/AA5221/A6R2.xlsx")
# DESCRIPTIVE STATISTICS
# mean, median, SD, and sample size for each group.
# INSTALL REQUIRED PACKAGE
# install.packages("dplyr")
# LOAD THE PACKAGE
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
##
##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
# CALCULATE THE DESCRIPTIVE STATISTICS
A6R2 %>%
group_by(ServiceType) %>%
summarise(
Mean = mean(SatisfactionScore, na.rm = TRUE),
Median = median(SatisfactionScore, na.rm = TRUE),
SD = sd(SatisfactionScore, na.rm = TRUE),
N = n()
)
## # A tibble: 2 × 5
## ServiceType Mean Median SD N
## <chr> <dbl> <dbl> <dbl> <int>
## 1 AI 3.6 3 1.60 100
## 2 Human 7.42 8 1.44 100
## # A tibble: 2 × 5
## ServiceType Mean Median SD N
## <chr> <dbl> <dbl> <dbl> <int>
## 1 AI 3.6 3 1.60 100
## 2 Human 7.42 8 1.44 100
# HISTOGRAMS
# CREATE THE HISTOGRAMS
# Replace "dataset" with your dataset name (without .xlsx)
# Replace "score" with your dependent variable R code name (example: USD)
# Replace "group" with your independent variable R code name (example: Country)
# Replace "Group1" with the R code name for your first group (example: USA)
# Replace "Group2" with the R code name for your second group (example: India)
hist(A6R2$SatisfactionScore[A6R2$ServiceType == "Human"],
main = "Histogram of Human Scores",
xlab = "Value",
ylab = "Frequency",
col = "lightblue",
border = "black",
breaks = 20)
hist(A6R2$SatisfactionScore[A6R2$ServiceType == "AI"],
main = "Histogram of AI Scores",
xlab = "Value",
ylab = "Frequency",
col = "lightgreen",
border = "black",
breaks = 20)
# QUESTIONS
# Answer the questions below as comments within the R script:
# Group 1 Scores
# The histogram is symmetrical but slightly negatively skewed.
# The histogram appears to have a proper bell shape.
# Group 2 Scores
# The histogram is positively skewed.
# The histogram appears too flat.
# ThE SHAPIRO-WILK TEST
shapiro.test(A6R2$SatisfactionScore[A6R2$ServiceType == "Human"])
##
## Shapiro-Wilk normality test
##
## data: A6R2$SatisfactionScore[A6R2$ServiceType == "Human"]
## W = 0.93741, p-value = 0.0001344
##
##Shapiro-Wilk normality test
##data: A6R2$SatisfactionScore[A6R2$ServiceType == "Human"]
##W = 0.93741, p-value = 0.0001344
shapiro.test(A6R2$SatisfactionScore[A6R2$ServiceType == "AI"])
##
## Shapiro-Wilk normality test
##
## data: A6R2$SatisfactionScore[A6R2$ServiceType == "AI"]
## W = 0.91143, p-value = 5.083e-06
##Shapiro-Wilk normality test
##
##data: A6R2$SatisfactionScore[A6R2$ServiceType == "AI"]
##W = 0.91143, p-value = 5.083e-06
# The data normally distributed for Variable 1?
# The data normally distributed for Variable 2?
# BOXPLOT
# INSTALL REQUIRED PACKAGE
install.packages("ggplot2")
## Installing package into 'C:/Users/dubet/AppData/Local/R/win-library/4.5'
## (as 'lib' is unspecified)
## package 'ggplot2' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\dubet\AppData\Local\Temp\RtmpYxaOJx\downloaded_packages
install.packages("ggpubr")
## Installing package into 'C:/Users/dubet/AppData/Local/R/win-library/4.5'
## (as 'lib' is unspecified)
## package 'ggpubr' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\dubet\AppData\Local\Temp\RtmpYxaOJx\downloaded_packages
# LOAD THE PACKAGE
library(ggplot2)
library(ggpubr)
# CREATE THE BOXPLOT
ggboxplot(A6R2, x = "ServiceType", y = "SatisfactionScore",
color = "ServiceType",
palette = "jco",
add = "jitter")
# There are dots outside of the boxplots and they mighty change the mean so much that the mean no longer accurately represents the average score?
# MANN-WHITNEY U TEST
wilcox.test(SatisfactionScore ~ ServiceType, data = A6R2, exact = FALSE)
##
## Wilcoxon rank sum test with continuity correction
##
## data: SatisfactionScore by ServiceType
## W = 497, p-value < 2.2e-16
## alternative hypothesis: true location shift is not equal to 0
# STATISTICAL SIGNIFICANCE
# P-value < 2.2e-16
# EFFECT-SIZE
install.packages("effectsize")
## Installing package into 'C:/Users/dubet/AppData/Local/R/win-library/4.5'
## (as 'lib' is unspecified)
## package 'effectsize' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\dubet\AppData\Local\Temp\RtmpYxaOJx\downloaded_packages
# LOAD THE PACKAGE
library(effectsize)
# C EFFECT SIZE (R VALUE)
library(rstatix)
##
## Attaching package: 'rstatix'
## The following objects are masked from 'package:effectsize':
##
## cohens_d, eta_squared
## The following object is masked from 'package:stats':
##
## filter
install.packages('coin')
## Installing package into 'C:/Users/dubet/AppData/Local/R/win-library/4.5'
## (as 'lib' is unspecified)
## package 'coin' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\dubet\AppData\Local\Temp\RtmpYxaOJx\downloaded_packages
rstatix::wilcox_effsize(A6R2, SatisfactionScore ~ ServiceType)
## # A tibble: 1 × 7
## .y. group1 group2 effsize n1 n2 magnitude
## * <chr> <chr> <chr> <dbl> <int> <int> <ord>
## 1 SatisfactionScore AI Human 0.784 100 100 large
# The size of the effect
# ± 0.50 to + = large
# Human Group had the higher average rank.
# The Mann-Whitney U test does not compare means directly.
# WRITTEN REPORT FOR MANN-WHITNEY U TEST
# A Mann-Whitney U test was conducted to compare satisfaction scores between participants who interacted with a human service provider (n = 100) and those who interacted with an AI service provider (n = 100). The results showed a statistically significant difference between the two groups (U = 497, p < .001). Participants in the human service condition reported higher median satisfaction scores (Mdn = 8) compared to participants in the AI service condition (Mdn = 3). The effect size, calculated using the rank-biserial correlation, was very large (r = -0.90), indicating a strong negative association between AI service type and satisfaction scores. Overall, these findings suggest that participants were significantly more satisfied with human service providers than with AI service providers.