Assignment 5

library(readxl)
library(ggpubr)

## Loading required package: ggplot2

A5Q1 <- read_excel("A5Q1.xlsx")

ggscatter(
  A5Q1,
  x = "age",
  y = "education",
  add = "reg.line",
  xlab = "Age",
  ylab = "Years of Education"
)

# The relationship is linear.
# The relationship is positive.
# There are no outliers.
mean(A5Q1$age)

## [1] 35.32634

sd(A5Q1$age)

## [1] 11.45344

median(A5Q1$age)

## [1] 35.79811

mean(A5Q1$education)

## [1] 13.82705

sd(A5Q1$education)

## [1] 2.595901

median(A5Q1$education)

## [1] 14.02915

hist(A5Q1$age,
     main = "Age",
     breaks = 20,
     col = "lightblue",
     border = "white",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

hist(A5Q1$education,
     main = "Education",
     breaks = 20,
     col = "lightcoral",
     border = "white",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

# Variable 1: Age
# The variable looks normally distributed.
# The data is symmetrical.
# The data has a proper bell curve.

# Variable 2: Education
# The variable looks normally distributed.
# The data is symmetrical.
# The data has a proper bell curve.
shapiro.test(A5Q1$age)

## 
##  Shapiro-Wilk normality test
## 
## data:  A5Q1$age
## W = 0.99194, p-value = 0.5581

shapiro.test(A5Q1$education)

## 
##  Shapiro-Wilk normality test
## 
## data:  A5Q1$education
## W = 0.9908, p-value = 0.4385

# Variable 1: Age
# The variable is normally distributed (p = .56).

# Variable 2: Education
# The variable is normally distributed (p = .44).
cor.test(A5Q1$age, A5Q1$education, method = "pearson")

## 
##  Pearson's product-moment correlation
## 
## data:  A5Q1$age and A5Q1$education
## t = 7.4066, df = 148, p-value = 9.113e-12
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.3924728 0.6279534
## sample estimates:
##       cor 
## 0.5200256

# A Pearson correlation was conducted to test the relationship between age (M = 35.33, SD = 11.45) and education (M = 13.83, SD = 2.60).

# There was a statistically significant relationship between the two variables, r(148) = .52, p < .001.

# The relationship was positive and strong.

# As age increased, education increased.


# Research Question 2

library(readxl)
A5Q2 <- read_excel("A5Q2.xlsx")
library(ggpubr)

ggscatter(
  A5Q2,
  x = "phone",
  y = "sleep",
  add = "reg.line",
  xlab = "Phone Use",
  ylab = "Sleep Duration"
)

# 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 = "Histogram of Phone Use",
     xlab = "Phone Use")

# Variable 1: Phone Use
# The variable looks abnormally distributed.
# The data is positively skewed.
# The data does not have a proper bell curve.
hist(A5Q2$sleep,
     main = "Histogram of Sleep Duration",
     xlab = "Sleep Duration")

# Variable 2: Sleep Duration
# The variable looks abnormally distributed.
# The data is negatively skewed.
# The data does not have a proper bell curve.

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 Use
# The variable is abnormally distributed (p < .001).

# Variable 2: Sleep Duration
# The variable is abnormally distributed (p < .001).
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 Spearman correlation was conducted to test the relationship between phone use (Mdn = 3.27) and sleep duration (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 use increased, sleep duration decreased.