library(readxl)
library(ggpubr)

## Loading required package: ggplot2

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

#creating the scatter plot
ggscatter(
  PhoneSleep,
  x = "phone",
  y = "sleep",
  add = "reg.line",
  xlab = "phone",
  ylab = "sleep"
)

#I fixed the code by swapping the independent and the dependent variables. Initially I had taken sleep as my #independent variable. Other than that throughout the code nothing was changed serve for the swap of independent and #dependent variables, the results of the experiment and tests remain the same.

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

#calculation of descriptive statistics

mean(PhoneSleep$phone)

## [1] 3.804609

sd(PhoneSleep$phone)

## [1] 2.661866

median(PhoneSleep$phone)

## [1] 3.270839

mean(PhoneSleep$sleep)

## [1] 7.559076

sd(PhoneSleep$sleep)

## [1] 1.208797

median(PhoneSleep$sleep)

## [1] 7.524099

#checking normality visually Histogram
hist(PhoneSleep$phone,
     main = "phone",
     breaks = 20,
     col = "lightblue",
     border = "white",
     xlab = "Hours of Phone Usage",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

# Variable 1: phone
# The variable looks abnormally distributed.


hist(PhoneSleep$sleep,
     main = "sleep",
     breaks = 20,
     col = "lightcoral",
     border = "white",
     xlab = "Hours of Sleep",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

# Variable 1: sleep hours
# The variable looks abnormally distributed.

shapiro.test(PhoneSleep$phone)

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

shapiro.test(PhoneSleep$sleep)

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

# Variable 1: phone
# The variable is abnormally distributed p < 0.05.

# Variable 2: sleep
# The variable is abnormally distributed p < 0.05.

#conducting a spearman correlation
cor.test(
  PhoneSleep$phone,
  PhoneSleep$sleep,
  method = "spearman"
)

## 
##  Spearman's rank correlation rho
## 
## data:  PhoneSleep$phone and PhoneSleep$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 use (M = 3.27) and sleep hours (M = 7.52).

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

# The relationship was negative and strong.

# As hours of phone usage increased, sleep hours decreased.