Assign 1: Q1

R Markdown

library(readxl)
library(ggpubr)

## Loading required package: ggplot2

library(ggplot2)
data_age <-read_excel("A4Q1.xlsx")

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

#The relationship is linear.

#The relationship is positive.

#The relationship is moderate.

#There are outliers

mean(data_age$age)

## [1] 35.32634

sd(data_age$age)

## [1] 11.45344

median(data_age$age)

## [1] 35.79811

mean(data_age$education)

## [1] 13.82705

sd(data_age$education)

## [1] 2.595901

median(data_age$education)

## [1] 14.02915

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

hist(data_age$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 symmetrical.
# The data has a proper bell curve.

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

shapiro.test(data_age$age)

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

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

shapiro.test(data_age$education)

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

#Shapiro-Wilk normality test
#data:  data_age$education
#W = 0.9908, p-value = 0.4385
#There is no evidence to reject normality for either variable.

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

## 
##  Pearson's product-moment correlation
## 
## data:  data_age$age and data_age$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 and education level.
#There was a statistically significant relationship between the two variables, r(148) = .52, p < .001.
#The relationship was positive and moderate.
#As age increased, education level increased.