A4Q1

library(readxl)
library(ggpubr)

## Warning: package 'ggpubr' was built under R version 4.4.3

## Loading required package: ggplot2

## Warning: package 'ggplot2' was built under R version 4.4.3

DatasetZ <- read_excel("C:/Users/niha/Downloads/A4Q1.xlsx")
ggscatter(
  DatasetZ,
  x = "age",
  y = "education",
  add = "reg.line",
  xlab = "age",
  ylab = "educaton"
)

## Warning: The `size` argument of `element_line()` is deprecated as of ggplot2 3.4.0.
## ℹ Please use the `linewidth` argument instead.
## ℹ The deprecated feature was likely used in the ggpubr package.
##   Please report the issue at <https://github.com/kassambara/ggpubr/issues>.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

## Warning: The `size` argument of `element_rect()` is deprecated as of ggplot2 3.4.0.
## ℹ Please use the `linewidth` argument instead.
## ℹ The deprecated feature was likely used in the ggpubr package.
##   Please report the issue at <https://github.com/kassambara/ggpubr/issues>.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

mean(DatasetZ$age)

## [1] 35.32634

sd(DatasetZ$age)

## [1] 11.45344

median(DatasetZ$age)

## [1] 35.79811

mean(DatasetZ$education)

## [1] 13.82705

sd(DatasetZ$education)

## [1] 2.595901

median(DatasetZ$education)

## [1] 14.02915

hist(DatasetZ$age,
     main = "age",
     breaks = 20,
     col = "red",
     border = "black",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

hist(DatasetZ$education,
     main = "education",
     breaks = 20,
     col = "blue",
     border = "grey",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

shapiro.test(DatasetZ$age)

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

shapiro.test(DatasetZ$education)

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

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

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