Assignment9

1.

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, therefore the probability of these results being random is very small.

chi-square test interpretation: There is a dependency between the promotion in the last 5 years and leaving.

non-technical interpretation: Employees that did not get a promotion within the last 5 years are more likely to leave.

Calculate proportions

prop_data <- hr %>%
  mutate(promotion_last_5years = as.factor(promotion_last_5years))%>%
  group_by(promotion_last_5years) %>%
  summarise(
    Stayed = sum(left == 0) / n(),
    Left = sum(left == 1) / n()
  )

Create stacked bar chart

plot_ly(prop_data) %>%
  add_bars(x = ~promotion_last_5years, y = ~Stayed, name = "Stayed", 
           marker = list(color = "#1f77b4")) %>%
  add_bars(x = ~promotion_last_5years, y = ~Left, name = "Left", 
           marker = list(color = "#ff7f0e")) %>%
  layout(
    barmode = "stack",
    xaxis = list(title = "Promotion in the Last 5 Years"),
    yaxis = list(title = "Proportion", tickformat = ",.0%"),
    title = "Employees that did not get a promotion \n are more likely to leave"
  )

2.

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, therefore the probability of these results being random is very small.

chi-square test interpretation: There is a dependency between having a work accident and leaving.

non-technical interpretation: Employees that had a work accident are more likely to stay.

Calculate proportions

prop_data2 <- hr %>%
  mutate(Work_accident = as.factor(Work_accident))%>%
  group_by(Work_accident) %>%
  summarise(
    Stayed = sum(left == 0) / n(),
    Left = sum(left == 1) / n()
  )

Create stacked bar chart

plot_ly(prop_data2) %>%
  add_bars(x = ~Work_accident, y = ~Stayed, name = "Stayed", 
           marker = list(color = "#1f77b4")) %>%
  add_bars(x = ~Work_accident, y = ~Left, name = "Left", 
           marker = list(color = "#ff7f0e")) %>%
  layout(
    barmode = "stack",
    xaxis = list(title = "Work_accident"),
    yaxis = list(title = "Proportion", tickformat = ",.0%"),
    title = "Employees that had a work \n accident are more likely to stay"
  )

3.

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, therefore the probability of these results being random is very small.

chi-square test interpretation: There is a dependency between salary level and leaving.

non-technical interpretation: Employees with the highest salary level are the most likely to stay, while low salary are the most likely to leave.

Calculate proportions

prop_data3 <- hr %>%
  group_by(salary) %>%
  summarise(
    Stayed = sum(left == 0) / n(),
    Left = sum(left == 1) / n()
  )

Create stacked bar chart

plot_ly(prop_data3) %>%
  add_bars(x = ~salary, y = ~Stayed, name = "Stayed", 
           marker = list(color = "#1f77b4")) %>%
  add_bars(x = ~salary, y = ~Left, name = "Left", 
           marker = list(color = "#ff7f0e")) %>%
  layout(
    barmode = "stack",
    xaxis = list(title = "Salary"),
    yaxis = list(title = "Proportion", tickformat = ",.0%"),
    title = "Employees with the highest salary level\nare the most likely to stay, while low \n salary are the most likely to leave"
  )

4.

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 (7.042e-15). The probability that these results could be random is very small.

chi-square test interpretation: There is a dependency between department and leaving.

non-technical interpretation: Employees that work within management and R&D are the most likely to stay.

Calculate proportions

prop_data4 <- hr %>%
  mutate(Department = as.factor(Department))%>%
  group_by(Department) %>%
  summarise(
    Stayed = sum(left == 0) / n(),
    Left = sum(left == 1) / n()
  )

Create stacked bar chart

plot_ly(prop_data4) %>%
  add_bars(x = ~Department, y = ~Stayed, name = "Stayed", 
           marker = list(color = "#1f77b4")) %>%
  add_bars(x = ~Department, y = ~Left, name = "Left", 
           marker = list(color = "#ff7f0e")) %>%
  layout(
    barmode = "stack",
    xaxis = list(title = "Department"),
    yaxis = list(title = "Proportion", tickformat = ",.0%"),
    title = "Employees that work within management and \n R&D are the most likely to stay"
  )