AA_Q2

library(readxl)
library(ggpubr)

## Loading required package: ggplot2

DatasetZ <- read_excel("C:/Users/manib/Downloads/A4Q2.xlsx")
ggscatter(
  DatasetZ,
  x = "phone",
  y = "sleep",
  add = "reg.line",
  xlab = "phone",
  ylab = "sleep"
)

# The relationship is linear.

# The relationship is negative.

# The relationship is moderate.

# There are outliers

mean(DatasetZ$phone)

## [1] 3.804609

sd(DatasetZ$phone)

## [1] 2.661866

median(DatasetZ$phone)

## [1] 3.270839

mean(DatasetZ$sleep)

## [1] 7.559076

sd(DatasetZ$sleep)

## [1] 1.208797

median(DatasetZ$sleep)

## [1] 7.524099

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

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

# Variable 1: phone
# The first variable looks normally distributed.
# The data is positively  symmetrical.
# The data does not have a proper bell curve.


# Variable 2: sleep
# The second variable looks normally distributed.
# The data is negitively symmetrical.
# The data does not have a proper bell curve.

shapiro.test(DatasetZ$phone)

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

shapiro.test(DatasetZ$sleep)

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

# Variable 1: phone
# The first variable is abnormally distributed (p = 0.000000009641).

# Variable 2: sleep
# The second variable is abnormally distributed (p = 0.00000008964).


cor.test(DatasetZ$phone, DatasetZ$sleep, method = "spearman")

## 
##  Spearman's rank correlation rho
## 
## data:  DatasetZ$phone and DatasetZ$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 Variable 1 (Mdn = 3.270) and Variable 2 (Mdn = 7.524).
# There was a statistically significant relationship between the two variables, ρ = -0.614, p<0.001.
# The relationship was negative and strong.
# As phone usage increased, sleep decreased.