Assignment 4_Q2

library(readxl)
library(ggpubr)

## Loading required package: ggplot2

A4Q2 <- read_excel("A4Q2.xlsx")

ggscatter(
  A4Q2,
  x = "sleep",
  y = "phone",
  add = "reg.line",
  xlab = "sleep",
  ylab = "phone"
)

# The relationship is linear.
# The relationship is negative.
# The relationship is moderate or strong.
# There are no outliers

mean(A4Q2$sleep)

## [1] 7.559076

sd(A4Q2$sleep)

## [1] 1.208797

median(A4Q2$sleep)

## [1] 7.524099

mean(A4Q2$phone)

## [1] 3.804609

sd(A4Q2$phone)

## [1] 2.661866

median(A4Q2$phone)

## [1] 3.270839

hist(A4Q2$sleep,
     main = "sleep",
     breaks = 20,
     col = "lightblue",
     border = "white",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

hist(A4Q2$phone,
     main = "phone",
     breaks = 20,
     col = "lightcoral",
     border = "white",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

# Variable 1: Sleep
# The first variable looks abnormally distributed.
# The data is negatively skewed .
# The data does not have a proper bell curve.


# Variable 2: Phone
# The second variable looks abnormally distributed.
# The data is positively skewed.
# The data does not have a proper bell curve.

shapiro.test(A4Q2$sleep)

## 
##  Shapiro-Wilk normality test
## 
## data:  A4Q2$sleep
## W = 0.91407, p-value = 8.964e-08

shapiro.test(A4Q2$phone)

## 
##  Shapiro-Wilk normality test
## 
## data:  A4Q2$phone
## W = 0.89755, p-value = 9.641e-09

# Variable 1: Sleep
# The first variable is abnormally distributed (p < .001).

# Variable 2: Phone
# The second variable is abnormally distributed (p < .001).

cor.test(A4Q2$sleep, A4Q2$phone, method = "spearman")

## 
##  Spearman's rank correlation rho
## 
## data:  A4Q2$sleep and A4Q2$phone
## S = 908390, p-value < 2.2e-16
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##        rho 
## -0.6149873

# A Spearman correlation was conducted to test the relationship between Variable 1 (Mdn = 7.52) and Variable 2 (Mdn = 3.27)
# There was a statistically significant relationship between the two variables, ρ = -.61, p < .001
# The relationship was negative and strong.
# As the hours of sleep increased, the hours of phone use decreased.