title: “Assignment 8: t-test - Employee Attrition Analysis” output: html_document ———————
Load Data
hr <- read_csv("https://raw.githubusercontent.com/aiplanethub/Datasets/refs/heads/master/HR_comma_sep.csv")
hr <- hr %>%
mutate(left_label = factor(left, levels = c(0, 1), labels = c("Stayed", "Left")))1. Satisfaction Level and Attrition
t1 <- t.test(satisfaction_level ~ left, data = hr)
t1##
## Welch Two Sample t-test
##
## data: satisfaction_level by 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 0.4400980Technical interpretation: The p-value is very small, which means the difference in mean satisfaction level between employees who stayed and employees who left is statistically significant.
Non-technical interpretation: Employees who left were generally less satisfied with their jobs than employees who stayed.
ggplot(hr, aes(x = left_label, y = satisfaction_level)) +
geom_boxplot() +
labs(
title = "Employees who left were generally less satisfied with their jobs than employees who stayed",
x = "Employee Status",
y = "Satisfaction Level"
) +
theme_minimal()
2. Last Evaluation and Attrition
t2 <- t.test(last_evaluation ~ left, data = hr)
t2##
## Welch Two Sample t-test
##
## data: last_evaluation by 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 0.7181126Technical interpretation: The p-value is very small, so the difference in mean last evaluation scores between employees who stayed and employees who left is statistically significant.
Non-technical interpretation: Employees who left tended to have slightly higher evaluation scores than employees who stayed.
ggplot(hr, aes(x = left_label, y = last_evaluation)) +
geom_boxplot() +
labs(
title = "Employees who left tended to have slightly higher evaluation scores than employees who stayed",
x = "Employee Status",
y = "Last Evaluation Score"
) +
theme_minimal()
3. Number of Projects and Attrition
t3 <- t.test(number_project ~ left, data = hr)
t3##
## Welch Two Sample t-test
##
## data: number_project by left
## t = -2.1663, df = 4236.5, p-value = 0.03034
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
## -0.131136535 -0.006540119
## sample estimates:
## mean in group 0 mean in group 1
## 3.786664 3.855503Technical interpretation: The p-value is very small, which means the difference in mean number of projects between employees who stayed and employees who left is statistically significant.
Non-technical interpretation: Employees who left usually worked on more projects than employees who stayed.
ggplot(hr, aes(x = left_label, y = number_project)) +
geom_boxplot() +
labs(
title = "Employees who left usually worked on more projects than employees who stayed",
x = "Employee Status",
y = "Number of Projects"
) +
theme_minimal()
4. Average Monthly Hours and Attrition
t4 <- t.test(average_montly_hours ~ left, data = hr)
t4##
## Welch Two Sample t-test
##
## data: average_montly_hours by 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 207.4192Technical interpretation: The p-value is very small, so the difference in mean average monthly hours between employees who stayed and employees who left is statistically significant.
Non-technical interpretation: Employees who left generally worked more hours per month than employees who stayed.
ggplot(hr, aes(x = left_label, y = average_montly_hours)) +
geom_boxplot() +
labs(
title = "Employees who left generally worked more hours per month than employees who stayed",
x = "Employee Status",
y = "Average Monthly Hours"
) +
theme_minimal()