#Import packages
library(readxl)
library(ggpubr)

## Loading required package: ggplot2

#import dataset

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

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

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

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

#create histogram for sleep and phone usage

hist(A5Q2$phone,
     main = "phone",
     breaks = 20,
     col = "lightblue",
     border = "white",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

hist(A5Q2$sleep,
     main = "sleep",
     breaks = 20,
     col = "lightcoral",
     border = "white",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

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

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

#check normality(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< .05).

# Variable 2: sleep
# The variable is abnormally distributed (p <.05).

#correlation to use (Spearman)
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< .001, p< .001.

# The relationship was negative and moderate.

# As the phone increased, sleep decreased.