library(readxl)
library(ggpubr)

## Loading required package: ggplot2

AgeEduation <- read_excel("C:/Users/tawan/OneDrive - Saint Louis University/AA 5221/Assignment 5/A5Q1.xlsx")
View(AgeEduation)

#creating the scatter plot
ggscatter(
  AgeEduation,
  x = "age",
  y = "education",
  add = "reg.line",
  xlab = "age",
  ylab = "education"
)

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

#calculating descriptive statistics

mean(AgeEduation$age)

## [1] 35.32634

sd(AgeEduation$age)

## [1] 11.45344

median(AgeEduation$age)

## [1] 35.79811

mean(AgeEduation$education)

## [1] 13.82705

sd(AgeEduation$education)

## [1] 2.595901

median(AgeEduation$education)

## [1] 14.02915

#checking normality visually (Histogram)

hist(AgeEduation$age,
     main = "Age",
     breaks = 20,
     col = "lightblue",
     border = "white",
     xlab = "Individual's Ages",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

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

hist(AgeEduation$education,
     main = "Education",
     breaks = 20,
     col = "lightcoral",
     border = "white",
     xlab = "Years of Education",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

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

#Check Normality Statistically (Shapiro-Wilk Test)
shapiro.test(AgeEduation$age)

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

shapiro.test(AgeEduation$education)

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

# Variable 1: Age
# The variable is normally distributed (p = .56).

# Variable 2: Education
# The variable is normally distributed (p = .44).


#Conducting Pearson correlation
cor.test(
  AgeEduation$age,
  AgeEduation$education,
  method = "pearson"
)

## 
##  Pearson's product-moment correlation
## 
## data:  AgeEduation$age and AgeEduation$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 age and (M = 35.33, SD = 11.45) and years of education (M = 13.82, SD = 2.59).

# There was a statistically significant relationship between the two variables, t(148) = .52, p < .05.

# The relationship was positive.

# As age increased, years of education increased.