library(readxl)
library(ggpubr)

## Loading required package: ggplot2

A5Q1 <- read_excel("//apporto.com/dfs/SLU/Users/brentgallagher_slu/Desktop/A5Q1.xls")
ggscatter(
A5Q1,
x = "age",
y = "education",
add = "reg.line",
xlab = "age",
ylab = "education"
)

# The relationship is linear. 
# The relationship is positive.
# There are 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",
cex.main = 1,
cex.axis = 1,
cex.lab = 1)

hist(A5Q1$education,
main = "education",
breaks = 20,
col = "lightcoral",
border = "white",
cex.main = 1,
cex.axis = 1,
cex.lab = 1)

# Variable 1: Age
# The variable looks abnormally distributed.
# The data is positively skewed.
# The data does not have a proper bell curve.

# Variable 2: Education
# The variable looks normally distributed.
# The data is symmetrical.
# 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 abnormally distributed (p = .55).

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

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

## 
##  Pearson's product-moment correlation
## 
## data:  A5Q1$age and A5Q1$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

# There is a strong relationship between the two variables.