aq41

Load libraries

library(readxl)
library(ggpubr) 

## Loading required package: ggplot2

 # Read the Excel file
A4Q1 <- read_excel("C:/Users/NITHIN KUMAR/Downloads/A4Q1.xlsx") 

ggscatter(
  A4Q1,
  x = "age",
  y = "education",
  add = "reg.line",
  xlab = "Age",
  ylab = "Education of the years"
)  

# The relationship is [linear].

# The relationship is [positive].

# The relationship is [ moderate).

# There has are outliers. 

mean(A4Q1$age)

## [1] 35.32634

sd(A4Q1$age)

## [1] 11.45344

median(A4Q1$age) 

## [1] 35.79811

mean(A4Q1$education)

## [1] 13.82705

sd(A4Q1$education)

## [1] 2.595901

median(A4Q1$education)  

## [1] 14.02915

hist(A4Q1$age, 
     main = "age",
     breaks = 20,
     col = "light green",
     border = "white",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

hist(A4Q1$education,
     main = "education",
     breaks = 20,
     col = "light blue",
     border = "white",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

# Age
# The age [ normally] distributed.
# The data is [symmetrical].
# The data has a proper bell curve. 

#education 
#The education looks normal distributed. 
#The data is symmetrical. 
#The data has a proper bell curve. 

shapiro.test(A4Q1$age) 

## 
##  Shapiro-Wilk normality test
## 
## data:  A4Q1$age
## W = 0.99194, p-value = 0.5581

#age 
# the first variable is normal (p= 0.5581)
shapiro.test(A4Q1$education) 

## 
##  Shapiro-Wilk normality test
## 
## data:  A4Q1$education
## W = 0.9908, p-value = 0.4385

#education 
# the variablbe is normal (p = 0.4385) 
 
cor.test(A4Q1$age, A4Q1$education, method = "pearson") 

## 
##  Pearson's product-moment correlation
## 
## data:  A4Q1$age and A4Q1$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(A4Q1$age, A4Q1$education, method = "spearman") 

## 
##  Spearman's rank correlation rho
## 
## data:  A4Q1$age and A4Q1$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 = 35.32634, SD = 11.45344) and education (M = 13.82705, SD = 2.595901).
# There was a statistically significant relationship between the two variables, r(df) = .148, p = 9.113e-12
# The relationship was weak. 
# As the independent variable increased, the dependent variable increase.  

# A Spearman correlation was conducted to test the relationship between (Mdn = 35.80, M = 35.33, SD = 11.45) and education (Mdn = 14.03, M = 13.83, SD = 2.60).
# There [was / was not] a statistically significant relationship between the two variables, ρ = 0.5244375, p = 2.2e-16.
# The relationship was positive.
# As the independent variable increased, the dependent variable increased.