chisq.test(hr$salary, hr$left)
##
## Pearson's Chi-squared test
##
## data: hr$salary and hr$left
## X-squared = 381.23, df = 2, p-value < 2.2e-16
p-value interpretation:
The p-value is very small (1.65e-83), so the probability these results
are random is very low.
chi-square test interpretation:
There is a dependence between salary and employee attrition.
non-technical interpretation:
Employees with lower salaries are more likely to leave.
prop_salary <- hr %>%
group_by(salary) %>%
summarise(
Stayed = sum(left == 0) / n(),
Left = sum(left == 1) / n()
)
plot_ly(prop_salary) %>%
add_bars(x = ~salary, y = ~Stayed, name = "Stayed") %>%
add_bars(x = ~salary, y = ~Left, name = "Left") %>%
layout(
barmode = "stack",
title = "Employees with lower salaries are more likely to leave",
xaxis = list(title = "Salary Level"),
yaxis = list(title = "Proportion", tickformat = ",.0%")
)
chisq.test(hr$Department, hr$left)
##
## Pearson's Chi-squared test
##
## data: hr$Department and hr$left
## X-squared = 86.825, df = 9, p-value = 7.042e-15
p-value interpretation:
The p-value is very small (7.04e-15), so the probability these results
are random is very low.
chi-square test interpretation:
There is a dependence between department and employee attrition.
non-technical interpretation:
Employees in some departments leave more than others.
prop_department <- hr %>%
group_by(Department) %>%
summarise(
Stayed = sum(left == 0) / n(),
Left = sum(left == 1) / n()
)
plot_ly(prop_department) %>%
add_bars(x = ~Department, y = ~Stayed, name = "Stayed") %>%
add_bars(x = ~Department, y = ~Left, name = "Left") %>%
layout(
barmode = "stack",
title = "Employees in some departments leave more than others",
xaxis = list(title = "Department"),
yaxis = list(title = "Proportion", tickformat = ",.0%")
)
chisq.test(hr$promotion_last_5years, hr$left)
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: hr$promotion_last_5years and hr$left
## X-squared = 56.262, df = 1, p-value = 6.344e-14
p-value interpretation:
The p-value is very small (6.34e-14), so the probability these results
are random is very low.
chi-square test interpretation:
There is a dependence between promotion status and employee
attrition.
non-technical interpretation:
Employees who were not promoted are more likely to leave.
prop_promotion <- hr %>%
group_by(promotion_last_5years) %>%
summarise(
Stayed = sum(left == 0) / n(),
Left = sum(left == 1) / n()
)
plot_ly(prop_promotion) %>%
add_bars(x = ~promotion_last_5years, y = ~Stayed, name = "Stayed") %>%
add_bars(x = ~promotion_last_5years, y = ~Left, name = "Left") %>%
layout(
barmode = "stack",
title = "Employees who were not promoted are more likely to leave",
xaxis = list(title = "Promotion in Last 5 Years (0 = No, 1 = Yes)"),
yaxis = list(title = "Proportion", tickformat = ",.0%")
)
chisq.test(hr$Work_accident, hr$left)
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: hr$Work_accident and hr$left
## X-squared = 357.56, df = 1, p-value < 2.2e-16
p-value interpretation:
The p-value is very small (9.56e-80), so the probability these results
are random is very low.
chi-square test interpretation:
There is a dependence between work accidents and employee attrition.
non-technical interpretation:
Employees with work accidents are less likely to leave.
prop_accident <- hr %>%
group_by(Work_accident) %>%
summarise(
Stayed = sum(left == 0) / n(),
Left = sum(left == 1) / n()
)
plot_ly(prop_accident) %>%
add_bars(x = ~Work_accident, y = ~Stayed, name = "Stayed") %>%
add_bars(x = ~Work_accident, y = ~Left, name = "Left") %>%
layout(
barmode = "stack",
title = "Employees with work accidents are less likely to leave",
xaxis = list(title = "Work Accident (0 = No, 1 = Yes)"),
yaxis = list(title = "Proportion", tickformat = ",.0%")
)