library(readxl)
library(ggpubr)

## Loading required package: ggplot2

A5Q1 <- read_excel("C:/Users/tmd97/Downloads/A5Q1.xlsx")
View(A5Q1)
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 normally distributed.
# The data is symmetrical skewed.
# The data has a proper bell curve.

# Variable 2: education
# The variable looks normally distributed.
# The data is symmetrical.
# The data does have 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 = .05).

# Variable 2: education
# The variable is normally distributed (p = .05).
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

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 Pearson correlation was conducted to test the relationship between age (M = 35.35634, SD = 11.45344) and education (M = 13.82705, SD = 2.595901).

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

# The relationship was positive and strong.

# As age increased, education decreased.
# A Spearman correlation was conducted to test the relationship between age (Mdn = 35.79811) and education (Mdn = 14.02915).

# There was a statistically significant relationship between the two variables, ρ = <2.2e-16, p = 0.5244375.

# The relationship was positive and strong.

# As the age increased, the education increased.
# age histogram was changed from negatively skewed to symmetrical. I was not originally sure if it was symmetrical enough that is why a said negatively skewed. 
# education histogram was changed from abnormally distributed to normally distributed. Because there were data points that I considered outliers that apparently are not actually considered outliers. So, I changed negatively skewed to symmetrical. I had chosen negatively skewed because I was taking symmetrical to literal not accounting for the fact that data points are not perfect. Which also explains why I needed to change not bell-shaped to there is a bell curve.  
# The Shapiro: age, I put the actual number not that it is p > .05.
# The Shapiro: education, I put the actual number and did not answer it as p > .05 the way we were instructed.
# I changed p = 9.113e-12 to p < .001. I keep forgetting to put the requested response and not the calculated answer. I will work on that.
# Pearson interpretation, I changed decreased to increased because as age increased, education also increased. I was being to literal and paid to close attention to the first 5 bars or so instead of looking at all of them as a whole.