library(readxl)
library(ggpubr)

## Loading required package: ggplot2

A5Q2_Sheet1_ <- read_excel("C:/Users/mercy/OneDrive - Saint Louis University/AA 5221/Assignment 5/A5Q2(Sheet1).xlsx")
View(A5Q2_Sheet1_)

#Create a Scatterplot
ggscatter(
  A5Q2_Sheet1_,
  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_Sheet1_$phone)

## [1] 3.804609

sd(A5Q2_Sheet1_$sleep)

## [1] 1.208797

median(A5Q2_Sheet1_$phone)

## [1] 3.270839

mean(A5Q2_Sheet1_$phone)

## [1] 3.804609

sd(A5Q2_Sheet1_$sleep)

## [1] 1.208797

median(A5Q2_Sheet1_$sleep)

## [1] 7.524099

#Check Normality Visually (Histograms)
hist(A5Q2_Sheet1_$phone,
     main = "phone",
     breaks = 20,
     col = "lightblue",
     border = "white",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

hist(A5Q2_Sheet1_$sleep,
     main = "sleep",
     breaks = 20,
     col = "lightcoral",
     border = "white",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

#Interpret the Histograms
# Variable 1: phone
# The variable is abnormally distributed.
# The data is negatively skewed.
# The data does not have a proper bell curve.

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

# Shapiro-Wilk Test
shapiro.test(A5Q2_Sheet1_$phone)

## 
##  Shapiro-Wilk normality test
## 
## data:  A5Q2_Sheet1_$phone
## W = 0.89755, p-value = 9.641e-09

shapiro.test(A5Q2_Sheet1_$sleep)

## 
##  Shapiro-Wilk normality test
## 
## data:  A5Q2_Sheet1_$sleep
## W = 0.91407, p-value = 8.964e-08

#Interpret the Shapiro-Wilk Test

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

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

#Determine Which Correlation to Use
#Use spearman's Correlation since the data is not normally distributed.
cor.test(
  A5Q2_Sheet1_$phone,
  A5Q2_Sheet1_$sleep,
  method = "spearman"
)

## 
##  Spearman's rank correlation rho
## 
## data:  A5Q2_Sheet1_$phone and A5Q2_Sheet1_$sleep
## S = 908390, p-value < 2.2e-16
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##        rho 
## -0.6149873

#Spearman Reporting 
# A Spearman correlation was conducted to test the relationship between phone (Mdn = 3.27) and sleep (Mdn = 7.52).
# There was not a statistically significant relationship between phone and sleep, ρ = 8.964e-08, p = 9.641e-09.
# The relationship was  negative and strong. 
# As the phone use increased, the sleep decreased.
''

## [1] ""