library(readxl)
library(ggpubr)

## Loading required package: ggplot2

A5Q2 <- read_excel("C:/Users/tmd97/Downloads/A5Q2.xlsx")
View(A5Q2)
ggscatter(
  A5Q2,
  x = "phone",
  y = "sleep",
  add = "reg.line",
  xlab = "phone",
  ylab = "sleep"
)

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

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 looks abnormally distributed.
# Variable 2: sleep looks abnormally distributed.

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 is abnormally distributed (p < .05).
# Variable 2: sleep is abnormally distributed (p < .05).
cor.test(
  A5Q2$phone,
  A5Q2$sleep,
  method = "pearson"
)

## 
##  Pearson's product-moment correlation
## 
## data:  A5Q2$phone and A5Q2$sleep
## t = -11.813, df = 148, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.7708489 -0.6038001
## sample estimates:
##        cor 
## -0.6966497

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 Pearson correlation was conducted to test the relationship between phone (M = 3.80, SD = 2.66) and sleep (M = 7.56, SD = 1.21).

# There was a statistically significant relationship between the two variables, r(148) = -0.70, p = <2.2e-16.

# The relationship was negative and strong.

# As phone increased, sleep decreased.
# 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 = < 2.2e-16, p = -0.61.

# The relationship was negative and strong.

# As the independent variable increased, the dependent variable decreased.
# I changed the sleep histogram from normally distributed to abnormally distributed to because it the p < .05 which makes it abnormal not 
# Shapiro phone, I changed the answer from the calculated answer to the preferred response we were told to use depending on where the actual answer fell. Which is p < .05.
# Shapiro sleep, I changed the answer from the calculated answer to the preferred response we were told to use depending on where the actual answer fell. Which is p < .05.
# Spearman: line 77. I was not sure about the order in which I should write which answer and ended up writing them in reverse. So, the answer is p = -.61, and p < .001. I had to also change the p-value to p < .001 because I used the answer I got when I calculated it and not the answer we were told to put depending on where the result of the calculation ended up.
# I changed weak to strong on line 79. Honestly, I think i just got confused because after reading the instructions, I am not sure how I confused them.