library(readxl)
library(ggpubr)
## Loading required package: ggplot2
A5Q2 <- read_excel("C:/Assignment 5/A5Q2.xlsx")

ggscatter(
  A5Q2,
  x = "sleep",
  y = "phone",
  add = "reg.line",
  xlab = "sleep",
  ylab = "phone"
)

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

mean(A5Q2$sleep)
## [1] 7.559076
sd(A5Q2$sleep)
## [1] 1.208797
median(A5Q2$sleep)
## [1] 7.524099
mean(A5Q2$phone)
## [1] 3.804609
sd(A5Q2$phone)
## [1] 2.661866
median(A5Q2$phone)
## [1] 3.270839
hist(A5Q2$sleep,
     main = "sleep",
     breaks = 20,
     col = "lightblue",
     border = "white")

hist(A5Q2$phone,
     main = "phone",
     breaks = 20,
     col = "lightcoral",
     border = "white")

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

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

shapiro.test(A5Q2$sleep)
## 
##  Shapiro-Wilk normality test
## 
## data:  A5Q2$sleep
## W = 0.91407, p-value = 8.964e-08
shapiro.test(A5Q2$phone)
## 
##  Shapiro-Wilk normality test
## 
## data:  A5Q2$phone
## W = 0.89755, p-value = 9.641e-09
# Variable 1: Sleep
# The variable is abnormally distributed (p = .000000089).

# Variable 2: Phone
# The variable is abnormally distributed (p = .0000000096).

cor.test(
  A5Q2$sleep,
  A5Q2$phone,
  method = "spearman"
)
## 
##  Spearman's rank correlation rho
## 
## data:  A5Q2$sleep and A5Q2$phone
## S = 908390, p-value < 2.2e-16
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##        rho 
## -0.6149873
# A Spearman's correlation was conducted to test the relationship between sleep (Mdn = 7.52) and phone (Mdn = 3.27).

# There was a statistically significant relationship between the two variables, ρ = -0.61, p < .001.

# The relationship was negative and strong.

# As the independent variable increased, the dependent variable decreased.