library(readxl)
library(ggpubr)
## Loading required package: ggplot2
data <- read_excel("C:/Users/kvpra/Documents/spring 2026/rlaanguage/A4Q2.xlsx")

ggscatter(
  data,
  x = "phone",
  y = "sleep",
  add = "reg.line",
  xlab = "Phone Usage",
  ylab = "Sleep Hours"
)

# The relationship is [linear].

# The relationship is [negative].

# The relationship is [moderate].

# There are [outliers].

mean(data$sleep)
## [1] 7.559076
sd(data$sleep)
## [1] 1.208797
median(data$sleep)
## [1] 7.524099
mean(data$phone)
## [1] 3.804609
sd(data$phone)
## [1] 2.661866
median(data$phone)
## [1] 3.270839
hist(data$sleep,
     main = "Sleep Distribution",
     breaks = 20,
     col = "lightblue",
     border = "white",
     xlab = "Sleep Hours",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

hist(data$phone,
     main = "Phone Usage Distribution",
     breaks = 20,
     col = "lightcoral",
     border = "white",
     xlab = "Phone Usage",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

# Variable 1: Sleep
# The first variable looks abnormally distributed.
# The data is symmetrical.
# The data has a proper bell curve.

# Variable 2: Phone Usage
# The second variable looks abnormally  distributed.
# The data is slightly positively skewed.
# The data does not have a perfect bell curve.

shapiro.test(data$sleep)
## 
##  Shapiro-Wilk normality test
## 
## data:  data$sleep
## W = 0.91407, p-value = 8.964e-08
shapiro.test(data$phone)
## 
##  Shapiro-Wilk normality test
## 
## data:  data$phone
## W = 0.89755, p-value = 9.641e-09
# Variable 1: Sleep
# The first variable is abnormally distributed (p < .001).

# Variable 2: Phone Usage
# The second variable is abnormally distributed (p < .001).

# Spearman Correlation
cor.test(data$phone, data$sleep, method = "spearman")
## 
##  Spearman's rank correlation rho
## 
## data:  data$phone and data$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 usage (Mdn = 3.27) and sleep (Mdn = 7.52).
#There was a statistically significant relationship between the two variables, ρ = -.61, p < .001.
#The relationship was negative and strong.
#As phone usage increased, sleep decreased.