1. Work Accident vs. Employee Status
chisq.test(hr$left , hr$Work_accident)
##
## 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
p-value interpretation: The p-value is very small,
therefore the probability of these results being random is very
small.
chi-square test interpretation: There is a
dependence between employee status and work accidents.
non-technical interpretation: Employees that had a
work accident are most likely to stay at the company.
prop_data <- hr %>%
group_by(Work_accident) %>%
summarise(
Left = sum(left == 1) / n(),
Stayed = sum(left == 0) / n(),
)
plot_ly(prop_data) %>%
add_bars(x = ~Work_accident, y = ~Left, name = "Left",
marker = list(color = "#9fcddd")) %>%
add_bars(x = ~Work_accident, y = ~Stayed, name = "Stayed",
marker = list(color = "#e9b4e3")) %>%
layout(
barmode = "stack",
xaxis = list(title = "Work Accident"),
yaxis = list(title = "Proportion", tickformat = ",.0%"),
title = "Employees that had a work accident are most likely to stay at the company"
)
3. Department vs. Employee Status
chisq.test(hr$left , hr$Department)
##
## Pearson's Chi-squared test
##
## data: hr$left and hr$Department
## X-squared = 86.825, df = 9, p-value = 7.042e-15
p-value interpretation: The p-value is very small,
therefore the probability of these results being random is very
small.
chi-square test interpretation: There is a
dependence between employee status and the department that they are
in.
non-technical interpretation: Employees are most
likely to stay in the company if they are in the management and RandD
departments.
prop_data3 <- hr %>%
group_by(Department) %>%
summarise(
Left = sum(left == 1) / n(),
Stayed = sum(left == 0) / n(),
)
plot_ly(prop_data3) %>%
add_bars(x = ~Department, y = ~Left, name = "Left",
marker = list(color = "#b0eada")) %>%
add_bars(x = ~Department, y = ~Stayed, name = "Stayed",
marker = list(color = "#c1b0ea")) %>%
layout(
barmode = "stack",
xaxis = list(title = "Department"),
yaxis = list(title = "Proportion", tickformat = ",.0%"),
title = "Employees are most likely to stay in the company
if they are in the management and RandD departments"
)
4. Salary vs. Employee Status
chisq.test(hr$left , hr$salary)
##
## Pearson's Chi-squared test
##
## data: hr$left and hr$salary
## X-squared = 381.23, df = 2, p-value < 2.2e-16
p-value interpretation: The p-value is very small,
therefore the probability of these results being random is very
small.
chi-square test interpretation: There is a
dependence between employee status and salary.
non-technical interpretation: Employees paid high
salaries are most likely to stay at the company.
prop_data4 <- hr %>%
group_by(salary) %>%
summarise(
Left = sum(left == 1) / n(),
Stayed = sum(left == 0) / n(),
)
plot_ly(prop_data4) %>%
add_bars(x = ~salary, y = ~Left, name = "Left",
marker = list(color = "#d28cca")) %>%
add_bars(x = ~salary, y = ~Stayed, name = "Stayed",
marker = list(color = "#c67569")) %>%
layout(
barmode = "stack",
xaxis = list(title = "Salary"),
yaxis = list(title = "Proportion", tickformat = ",.0%"),
title = "Employees paid high salaries are most likely to stay at the company"
)