Assignment 7

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(ggplot2)

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.

Correlation 1: Satisfaction Level vs Average Monthly Hours

 cor.test(hr$satisfaction_level, hr$average_montly_hours)

## 
##  Pearson's product-moment correlation
## 
## data:  hr$satisfaction_level and hr$average_montly_hours
## t = -2.4556, df = 14997, p-value = 0.01408
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.036040356 -0.004045605
## sample estimates:
##         cor 
## -0.02004811

Interpret the results in technical terms: The p-value exceeded the 0.01 cutoff point. The correlation is between -0.1 and 0 whichs suggests no correlation.

Interpret the results in non-technical terms: There is no relationship between Average Monthly Hours and Satisfaction Level.

ggplot(hr, aes(x = average_montly_hours, y = satisfaction_level)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE, color = "red") +
  labs(title = "There is no Relationship Between Average Monthly Hours and Satisfaction Level",
       x = "Average Monthly Hours",
       y = "Satisfaction Level")

## `geom_smooth()` using formula = 'y ~ x'

Correlation 2: Satisfaction Level vs Number of Projects

cor.test(hr$satisfaction_level, hr$number_project)

## 
##  Pearson's product-moment correlation
## 
## data:  hr$satisfaction_level and hr$number_project
## t = -17.69, df = 14997, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.1586105 -0.1272570
## sample estimates:
##        cor 
## -0.1429696

Interpret the results in technical terms: The p-value is within the 0.01 cutoff point. The correlation suggests that there is a weak negative correlation.

Interpret the results in non-technical terms: As satisfaction level decreases, the number of projects increases slightly.

ggplot(hr, aes(x = number_project, y = satisfaction_level)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE, color = "red") +
  labs(title = "As Satisfaction Level Decreases, the Number of Projects Increases Slightly",
       x = "Number of Projects",
       y = "Satisfaction Level")

## `geom_smooth()` using formula = 'y ~ x'

Correlation 3: Satisfaction Level vs Last Evaluation Score

cor.test(hr$satisfaction_level, hr$last_evaluation)

## 
##  Pearson's product-moment correlation
## 
## data:  hr$satisfaction_level and hr$last_evaluation
## t = 12.933, df = 14997, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.08916727 0.12082195
## sample estimates:
##       cor 
## 0.1050212

Interpret the results in technical terms: The p-value is within the 0.01 cutoff point. The correlation suggests a weak positive correlation.

Interpret the results in non-technical terms: As satisfaction level increases, the evaluation score increases slightly.

ggplot(hr, aes(x = last_evaluation, y = satisfaction_level)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE, color = "red") +
  labs(title = " As Satisfaction Level Increases, the Evaluation Score Increases Slightly",
       x = "Last Evaluation Score",
       y = "Satisfaction Level")

## `geom_smooth()` using formula = 'y ~ x'

Correlation 4: Satisfaction Level vs Time Spent at the Company

cor.test(hr$satisfaction_level, hr$time_spend_company)

## 
##  Pearson's product-moment correlation
## 
## data:  hr$satisfaction_level and hr$time_spend_company
## t = -12.416, df = 14997, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.11668153 -0.08499948
## sample estimates:
##        cor 
## -0.1008661

Interpret the results in technical terms: The p-value is within the 0.01 cutoff point. The correlation suggests that there is a weak negative correlation.

Interpret the results in non-technical terms: As satisfaction level decreases, the time spent at the company increases.

ggplot(hr, aes(x = time_spend_company, y = satisfaction_level)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE, color = "red") +
  labs(title = "As Satisfaction Level Decreases, the Time spent at the Company Increases",
       x = "Time Spent at Company",
       y = "Satisfaction Level")

## `geom_smooth()` using formula = 'y ~ x'