library(readxl)
library(ggpubr)

## Loading required package: ggplot2

A5Q2 <- read_excel("C:/Users/onhau01/OneDrive - Saint Louis University/AA 5221/Assignment 5/A5Q2.xlsx")

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

#Interpret the Scatterplot

# The relationship is linear.
# The relationship is negative.
# There are outliers.

#Calculate Descriptive Statistics
mean(A5Q2$phone)

## [1] 3.804609

sd(A5Q2$phone)

## [1] 2.661866

median(A5Q2$phone)

## [1] 3.270839

mean(A5Q2$sleep)

## [1] 7.559076

sd(A5Q2$sleep)

## [1] 1.208797

median(A5Q2$sleep)

## [1] 7.524099

#Check Normality Visually (Histograms)
hist(A5Q2$phone,
     main = "phone",
     breaks = 20,
     col = "lightblue",
     border = "white")

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

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

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

#Check Normality Statistically (Shapiro-Wilk Test)
shapiro.test(A5Q2$phone)

## 
##  Shapiro-Wilk normality test
## 
## data:  A5Q2$phone
## W = 0.89755, p-value = 9.641e-09

shapiro.test(A5Q2$sleep)

## 
##  Shapiro-Wilk normality test
## 
## data:  A5Q2$sleep
## W = 0.91407, p-value = 8.964e-08

# Variable 1: Phone
# The variable is abnormally distributed (p = 9.641e-09).

# Variable 2: Sleep
# The variable is abnormally distributed (p = 8.964e-08).

#Conduct a Spearman Correlation
cor.test(
  A5Q2$phone,
  A5Q2$sleep,
  method = "spearman"
)

## 
##  Spearman's rank correlation rho
## 
## data:  A5Q2$phone and A5Q2$sleep
## 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 phone (Mdn = 3.27) and sleep (Mdn = 7.52).

# There was a statistically significant relationship between the two variables, ρ = -.61, p = .001.

# The relationship was negative and strong.

# As the phone increased, the sleep decreased.