library(readxl)
library(ggpubr)
## Loading required package: ggplot2
A4Q1 <- read_excel("A4Q1.xlsx")
ggscatter(
  A4Q1,
  x = "age",
  y = "education",
  add = "reg.line",
  xlab = "Age",
  ylab = "Years of Education"
)

# The relationship is linear.
# The relationship is positive.
# The relationship is moderate.
# There are no meaningful outliers.
mean(A4Q1$age)
## [1] 35.32634
sd(A4Q1$age)
## [1] 11.45344
median(A4Q1$age)
## [1] 35.79811
mean(A4Q1$education)
## [1] 13.82705
sd(A4Q1$education)
## [1] 2.595901
median(A4Q1$education)
## [1] 14.02915
hist(A4Q1$age,
     main = "age",
     breaks = 20,
     col = "lightblue",
     border = "white",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

hist(A4Q1$education,
     main = "education",
     breaks = 20,
     col = "lightcoral",
     border = "white",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

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

#Variable 2: Education
#The second variable looks normally distributed.
#The data is approximately symmetrical
#The data has a proper bell curve.

shapiro.test(A4Q1$age)
## 
##  Shapiro-Wilk normality test
## 
## data:  A4Q1$age
## W = 0.99194, p-value = 0.5581
shapiro.test(A4Q1$education)
## 
##  Shapiro-Wilk normality test
## 
## data:  A4Q1$education
## W = 0.9908, p-value = 0.4385
#Variable 1: Age
#The first variable is normally distributed (p=0.5581).
#Variable 2: Education
#The second variable is normally distributed (p=0.4385).
#Overall data is normal. Use Pearson Correlation.

cor.test(
  A4Q1$age,
  A4Q1$education,
  method = "pearson"
  )
## 
##  Pearson's product-moment correlation
## 
## data:  A4Q1$age and A4Q1$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 a person's age in years (M = 35.33, SD = 11.45) and years of education (M = 13.83, SD = 2.60).
#There was a statistically significant relationship between the two variables, r(148) = .52, p < .001.
#The relationship was positive and moderate.
#As age increased, years of education also increased.

A pearson correlation was conducted to test the relationship between a person’s age in years (M = 35.33, SD = 11.45) and years of education (M = 13.83, SD = 2.60).

There was a statistically significant relationship between the two variables, r(148) = .52, p < .001.

The relationship was positive and moderate.

As age increased, years of education also increased.