library(readxl)
library(ggpubr)

## Loading required package: ggplot2

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

ggscatter(
  A5Q2_Sheet1_,
  x="phone",
  y="sleep",
  add = "reg.line",
  xlab = "phone",
  ylab = "sleep"
)

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

#for IV(Phone)

mean(A5Q2_Sheet1_$phone)

## [1] 3.804609

sd(A5Q2_Sheet1_$phone)

## [1] 2.661866

median(A5Q2_Sheet1_$phone)

## [1] 3.270839

#for DV (sleep)

mean(A5Q2_Sheet1_$sleep)

## [1] 7.559076

sd(A5Q2_Sheet1_$sleep)

## [1] 1.208797

median(A5Q2_Sheet1_$sleep)

## [1] 7.524099

#histogram
#phone

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

#sleep

hist(A5Q2_Sheet1_$sleep,
     main = "phone",
     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 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

# Variable 1: phone
# The variable is Abnormally distributed (p < .001).

# Variable 2: sleep
# The variable is Abnormally distributed (p < .001).

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

# 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, p= -0.61, p < .001

# The relationship was negative and moderate.

# As the independent variable (phone) increased, the dependent variable (sleep) decreased.