library(readr)
library(plotly)
## Loading required package: ggplot2
##
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
##
## last_plot
## The following object is masked from 'package:stats':
##
## filter
## The following object is masked from 'package:graphics':
##
## layout
hr <- read_csv('https://raw.githubusercontent.com/aiplanethub/Datasets/refs/heads/master/HR_comma_sep.csv')
## Rows: 14999 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): Department, salary
## dbl (8): satisfaction_level, last_evaluation, number_project, average_montly...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
T.Test 1
t.test(hr$satisfaction_level ~ hr$left)
##
## Welch Two Sample t-test
##
## data: hr$satisfaction_level by hr$left
## t = 46.636, df = 5167, p-value < 2.2e-16
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
## 0.2171815 0.2362417
## sample estimates:
## mean in group 0 mean in group 1
## 0.6668096 0.4400980
p-value < .01 → Significant difference
Employees who stayed (M = 0.67) had higher satisfaction than those
who left (M = 0.44)
People who left were less satisfied with their jobs
plot_ly(hr,
x = ~factor(left, labels = c("Stayed", "Left")),
y = ~satisfaction_level,
type = "box",
color = ~factor(left, labels = c("Stayed", "Left"))) %>%
layout(title = "Employees Who Left Were Less Satisfied With Their Jobs",
xaxis = list(title = "Employment Status"),
yaxis = list(title = "Satisfaction Level"),
showlegend = FALSE)
T.Test 2
t.test(hr$last_evaluation ~ hr$left)
##
## Welch Two Sample t-test
##
## data: hr$last_evaluation by hr$left
## t = -0.72534, df = 5154.9, p-value = 0.4683
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
## -0.009772224 0.004493874
## sample estimates:
## mean in group 0 mean in group 1
## 0.7154734 0.7181126
p-value = 0.47 → Not significant
No difference in evaluation scores between employees who left and
stayed
T.Test 3
t.test(hr$average_montly_hours ~ hr$left)
##
## Welch Two Sample t-test
##
## data: hr$average_montly_hours by hr$left
## t = -7.5323, df = 4875.1, p-value = 5.907e-14
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
## -10.534631 -6.183384
## sample estimates:
## mean in group 0 mean in group 1
## 199.0602 207.4192
p-value < .01 → Significant difference
Employees who left (M = 207.4) worked more hours than those who
stayed (M = 199.1)
People who left worked longer hours each month
plot_ly(hr,
x = ~factor(left, labels = c("Stayed", "Left")),
y = ~average_montly_hours,
type = "box",
color = ~factor(left, labels = c("Stayed", "Left"))) %>%
layout(title = "Employees Who Left Worked More Hours Per Month",
xaxis = list(title = "Employment Status"),
yaxis = list(title = "Average Monthly Hours"),
showlegend = FALSE)
T.Test 4
t.test(hr$time_spend_company ~ hr$left)
##
## Welch Two Sample t-test
##
## data: hr$time_spend_company by hr$left
## t = -22.631, df = 9625.6, p-value < 2.2e-16
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
## -0.5394767 -0.4534706
## sample estimates:
## mean in group 0 mean in group 1
## 3.380032 3.876505
p-value < .01 → Significant difference
Employees who left (M = 3.88) worked longer than those who stayed (M
= 3.38)
People who left had been at the company longer
plot_ly(hr,
x = ~factor(left, labels = c("Stayed", "Left")),
y = ~time_spend_company,
type = "box",
color = ~factor(left, labels = c("Stayed", "Left"))) %>%
layout(title = "Employees Who Left Had Been at the Company Longer",
xaxis = list(title = "Employment Status"),
yaxis = list(title = "Years at Company"),
showlegend = FALSE)