Holiday

library(readxl)
mydata <- read_xlsx("./Holiday.xlsx")
mydata <- as.data.frame(mydata)

head(mydata)

##   ID Budget  Status
## 1  1    300 Student
## 2  2    400 Student
## 3  3    200 Student
## 4  4    100 Student
## 5  5    400 Student
## 6  6    100 Student

Description of the variables:

• ID: ID of a person
• Budget: Amount of money they are planning to spend on a holiday.
• Status: Student, Employed or Retired.

mydata$Status <- as.factor(mydata$Status)

library(ggplot2)
ggplot(mydata, aes(x = Status, y = Budget)) +
  geom_violin(fill = "grey90", alpha = 0.6, trim = FALSE) +
  geom_boxplot(width = 0.1, fill = "grey60", outlier.shape = NA) +
  labs(title = "Distribution of Holiday Budget by Status",
       x = "Status",
       y = "Planned Holiday Budget") +
  theme_bw()

library(rstatix)

## 
## Attaching package: 'rstatix'

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

mydata %>%
  group_by(Status) %>%
  get_summary_stats(Budget, type = "median_iqr")

## # A tibble: 3 × 5
##   Status   variable     n median   iqr
##   <fct>    <fct>    <dbl>  <dbl> <dbl>
## 1 Employed Budget      45    600   300
## 2 Retired  Budget      18    300   200
## 3 Student  Budget      30    250   200

library(rstatix)

mydata %>%
  group_by(Status) %>%
  shapiro_test(Budget)

## # A tibble: 3 × 4
##   Status   variable statistic       p
##   <fct>    <chr>        <dbl>   <dbl>
## 1 Employed Budget       0.968 0.239  
## 2 Retired  Budget       0.900 0.0575 
## 3 Student  Budget       0.892 0.00527

kruskal.test(Budget ~ Status, 
             data = mydata)

## 
##  Kruskal-Wallis rank sum test
## 
## data:  Budget by Status
## Kruskal-Wallis chi-squared = 36.798, df = 2, p-value =
## 1.022e-08

kruskal_effsize(Budget ~ Status, 
                data = mydata)

## # A tibble: 1 × 5
##   .y.        n effsize method  magnitude
## * <chr>  <int>   <dbl> <chr>   <ord>    
## 1 Budget    93   0.387 eta2[H] large

library(rstatix)

groups_nonpar <- wilcox_test(Budget ~ Status,
                             paired = FALSE,
                             p.adjust.method = "bonferroni",
                             data = mydata)

groups_nonpar

## # A tibble: 3 × 9
##   .y.    group1   group2     n1    n2 statistic             p    p.adj
## * <chr>  <chr>    <chr>   <int> <int>     <dbl>         <dbl>    <dbl>
## 1 Budget Employed Retired    45    18      660. 0.0000415      1.25e-4
## 2 Budget Employed Student    45    30     1190. 0.00000000114  3.41e-9
## 3 Budget Retired  Student    18    30      330  0.196          5.87e-1
## # ℹ 1 more variable: p.adj.signif <chr>