library(readr)
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(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
# Load dataset
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.
# Convert appropriate variables to factors
hr$left <- factor(hr$left, labels = c("Stayed", "Left"))
hr$salary <- factor(hr$salary)
hr$promotion_last_5years <- factor(hr$promotion_last_5years)
hr$Work_accident <- factor(hr$Work_accident)
hr$Department <- factor(hr$Department)
TEST 1: Salary vs Left
test1 <- chisq.test(hr$left, hr$salary)
test1
##
## Pearson's Chi-squared test
##
## data: hr$left and hr$salary
## X-squared = 381.23, df = 2, p-value < 2.2e-16
Technical interpretation:
- p < .001 → there is a statistically significant association
between salary and leaving.
- Employees with different salary levels leave at different
rates.
Non-technical interpretation:
- Employees with low salaries are far more likely to leave than those
with medium or high salaries.
# Plot
salary_prop <- hr %>%
group_by(salary, left) %>%
summarise(count = n(), .groups = "drop") %>%
mutate(prop = count / sum(count))
plot_ly(salary_prop, x = ~salary, y = ~prop, color = ~left, type = "bar") %>%
layout(
title = "Employees with low salaries are far more likely to leave",
xaxis = list(title = "Salary Level"),
yaxis = list(title = "Proportion"),
barmode = "group"
)
TEST 3: Work Accident vs Left
test3 <- chisq.test(hr$left, hr$Work_accident)
test3
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: hr$left and hr$Work_accident
## X-squared = 357.56, df = 1, p-value < 2.2e-16
Technical interpretation:
- p < .001 → there is a statistically significant association
between work accidents and leaving.
- Employees with or without accidents leave at different rates.
Non-technical interpretation:
- Employees who experienced work accidents are less likely to leave
the company.
# Plot
accident_prop <- hr %>%
group_by(Work_accident, left) %>%
summarise(count = n(), .groups = "drop") %>%
mutate(prop = count / sum(count))
plot_ly(accident_prop, x = ~Work_accident, y = ~prop, color = ~left, type = "bar") %>%
layout(
title = "Employees with accidents are less likely to leave",
xaxis = list(title = "Work Accident (0 = No, 1 = Yes)"),
yaxis = list(title = "Proportion"),
barmode = "group"
)
TEST 4: Department vs Left
test4 <- chisq.test(hr$left, hr$Department)
test4
##
## Pearson's Chi-squared test
##
## data: hr$left and hr$Department
## X-squared = 86.825, df = 9, p-value = 7.042e-15
Technical interpretation:
- p < .001 → there is a statistically significant association
between department and leaving.
- Employees from different departments leave at different rates.
Non-technical interpretation:
- Employees from certain departments such as technical and sales are
more likely to leave than others. This might be because these
departments have more employees overall.
# Plot
dept_prop <- hr %>%
group_by(Department, left) %>%
summarise(count = n(), .groups = "drop") %>%
mutate(prop = count / sum(count))
plot_ly(dept_prop, x = ~Department, y = ~prop, color = ~left, type = "bar") %>%
layout(
title = "Employees from some departments are more likely to leave",
xaxis = list(title = "Department"),
yaxis = list(title = "Proportion"),
barmode = "group"
)