Assignment 8

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

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.

TEST 1:

hr <- hr %>% mutate(left = factor(left, labels = c("Stayed", "Left")))

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 Stayed and group Left is not equal to 0
## 95 percent confidence interval:
##  0.2171815 0.2362417
## sample estimates:
## mean in group Stayed   mean in group Left 
##            0.6668096            0.4400980

plot_ly(hr,
        x = ~left,
        y = ~satisfaction_level,
        type = "box") %>%
  layout(title = "Employees who left had lower satisfaction levels")

TEST 2:

t2 <- t.test(average_montly_hours ~ left, data = hr)
t2

## 
##  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 Stayed and group Left is not equal to 0
## 95 percent confidence interval:
##  -10.534631  -6.183384
## sample estimates:
## mean in group Stayed   mean in group Left 
##             199.0602             207.4192

plot_ly(hr,
        x = ~left,
        y = ~average_montly_hours,
        type = "box") %>%
  layout(title = "Employees who left tended to work more hours")

TEST 3:

t3 <- t.test(last_evaluation ~ left, data = hr)
t3

## 
##  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 Stayed and group Left is not equal to 0
## 95 percent confidence interval:
##  -0.009772224  0.004493874
## sample estimates:
## mean in group Stayed   mean in group Left 
##            0.7154734            0.7181126

plot_ly(hr,
        x = ~left,
        y = ~last_evaluation,
        type = "box") %>%
  layout(title = "Employees who left had different evaluation scores")

TEST 4:

t4 <- t.test(time_spend_company ~ left, data = hr)
t4

## 
##  Welch Two Sample t-test
## 
## data:  time_spend_company by left
## t = -22.631, df = 9625.6, p-value < 2.2e-16
## alternative hypothesis: true difference in means between group Stayed and group Left is not equal to 0
## 95 percent confidence interval:
##  -0.5394767 -0.4534706
## sample estimates:
## mean in group Stayed   mean in group Left 
##             3.380032             3.876505

plot_ly(hr,
        x = ~left,
        y = ~time_spend_company,
        type = "box") %>%
  layout(title = "Employees who left spent more years at the company")