Andrew DeLaricheliere

DATA3210

Assignment 9

Load libraries:

library(readr)

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.

Chi-Squared Test:

chisq.test(table(hr$left, hr$salary))

## 
##  Pearson's Chi-squared test
## 
## data:  table(hr$left, hr$salary)
## X-squared = 381.23, df = 2, p-value < 2.2e-16

Graph:

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

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

prop_data <- hr %>%
  group_by(salary) %>%
  summarise(
    stayed = sum(left == 0) / n(),
    left = sum(left == 1) / n()
  ) %>%
  mutate(salary = factor(salary, levels = c("low", "medium", "high")))

plot_ly(prop_data) %>%
  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 Level"),
    yaxis = list(title = "Proportion"),
    title = "Employees with lower salaries are more likely to leave"
  )

Interpretations:

# P-Value Interpretation: The p-value is extremely small, making it very unlikely that the results are due to chance.

# Technical interpretation: There is a dependency between left and salary.

# Non-Technical Interpretation: Employees with lower salaries are more likely to leave.