library(readxl)
library(ggpubr)

## Loading required package: ggplot2

A5Q1 <- read_excel("C:/Assignment 5/A5Q1.xlsx")

ggscatter(
  A5Q1,
  x = "age",
  y = "education",
  add = "reg.line",
  xlab = "age",
  ylab = "education"
)

# The relationship is linear.
# The relationship is positive.
# There are no outliers.

mean(A5Q1$age)

## [1] 35.32634

sd(A5Q1$age)

## [1] 11.45344

median(A5Q1$age)

## [1] 35.79811

mean(A5Q1$education)

## [1] 13.82705

sd(A5Q1$education)

## [1] 2.595901

median(A5Q1$education)

## [1] 14.02915

hist(A5Q1$age,
     main = "Age",
     breaks = 20,
     col = "lightblue",
     border = "white")

hist(A5Q1$education,
     main = "Education",
     breaks = 20,
     col = "lightcoral",
     border = "white")

# Variable 1: age
# The variable looks normally distributed.
# The data is symmetrical.
# The data has a proper bell curve.

# Variable 2: education
# The variable looks normally distributed.
# The data is positively skewed.
# The data has a proper bell curve.

shapiro.test(A5Q1$age)

## 
##  Shapiro-Wilk normality test
## 
## data:  A5Q1$age
## W = 0.99194, p-value = 0.5581

shapiro.test(A5Q1$education)

## 
##  Shapiro-Wilk normality test
## 
## data:  A5Q1$education
## W = 0.9908, p-value = 0.4385

# Variable 1: Age
# The variable is normally distributed (p = .55).

# Variable 2: Education
# The variable is abnormally distributed (p = .43).

cor.test(
  A5Q1$age,
  A5Q1$education,
  method = "spearman"
)

## 
##  Spearman's rank correlation rho
## 
## data:  A5Q1$age and A5Q1$education
## S = 267492, p-value < 2.2e-16
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.5244375

# A Spearman's correlation was conducted to test the relationship between Age (Mdn = 35.79) and Education (Mdn = 14.02).

# There was a statistically significant relationship between the two variables, ρ = .52, p < .001.

# The relationship was positive and moderate.

# As the independent variable increased, the dependent variable increased.