A4Q1

library(readxl)
library(ggpubr)

## Loading required package: ggplot2

DatasetZ <- read_excel("C:/Users/sanja/Downloads/A4Q1.xlsx")

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

  mean(DatasetZ$age)

## [1] 35.32634

  sd(DatasetZ$age)

## [1] 11.45344

  median(DatasetZ$age)

## [1] 35.79811

  mean(DatasetZ$education)

## [1] 13.82705

  sd(DatasetZ$education)

## [1] 2.595901

  median(DatasetZ$education)

## [1] 14.02915

  hist(DatasetZ$age,
       main = "age",
       breaks = 20,
       col = "lightblue",
       border = "white",
       cex.main = 1,
       cex.axis = 1,
       cex.lab = 1)

  hist(DatasetZ$education,
       main = "education",
       breaks = 20,
       col = "lightcoral",
       border = "white",
       cex.main = 1,
       cex.axis = 1,
       cex.lab = 1)

  # The relationship is [linear].
  
  # The relationship is [positive].
  
  # The relationship is [moderate].
  
  # There [are no] outliers.
  
  # Variable 1: age
  # The first variable looks [normally] distributed.
  # The data is [ positively skewed].
  # The data [does not have] a proper bell curve.
  # Variable 2: education
  # The second variable  looks [ normally] distributed.
  # The data is [ positively skewed].
  # The data [does not have] a proper bell curve.
  shapiro.test(DatasetZ$age)

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

  shapiro.test(DatasetZ$education)

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

  # Variable 1: age
  # The first variable is [normally ] distributed (p = .55).
  
  # Variable 2: education
  # The second variable is [normally ] distributed (p = .43).
  cor.test(DatasetZ$age, DatasetZ$education, method = "pearson")

## 
##  Pearson's product-moment correlation
## 
## data:  DatasetZ$age and DatasetZ$education
## t = 7.4066, df = 148, p-value = 9.113e-12
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.3924728 0.6279534
## sample estimates:
##       cor 
## 0.5200256

  # A Pearson correlation was conducted to test the relationship between Variable 1 (M = 35.32, SD = 11.45) and Variable 2 (M = 13.82, SD = 2.59).
  # There [was] a statistically significant relationship between the two variables, r(148) = .52, p ,0.01.
  # The relationship was positive.
  # As the age increased, the education increased.