opening the installed packages

library(readxl)
library(ggpubr)
## Loading required package: ggplot2

importing data sets

datasetA <- read_excel("C:/Users/pavan/Downloads/DatasetA.xlsx")
datasetB <- read_excel("C:/Users/pavan/Downloads/DatasetB.xlsx")

datasetA

Calculate the Descriptive Statistics for datasetA

mean(datasetA$StudyHours)
## [1] 6.135609
sd(datasetA$StudyHours)
## [1] 1.369224
mean(datasetA$ExamScore)
## [1] 90.06906
sd(datasetA$ExamScore)
## [1] 6.795224

Create Histograms & Visually Check Normality

hist(datasetA$StudyHours,
     main = "StudyHours",
     breaks = 10,
     col = "red",
     border = "white",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

hist(datasetA$ExamScore,
     main = "ExamScore",
     breaks = 10,
     col = "green",
     border = "white",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

Statistically Test Normality

shapiro.test(datasetA$StudyHours) 
## 
##  Shapiro-Wilk normality test
## 
## data:  datasetA$StudyHours
## W = 0.99388, p-value = 0.9349
shapiro.test(datasetA$ExamScore)
## 
##  Shapiro-Wilk normality test
## 
## data:  datasetA$ExamScore
## W = 0.96286, p-value = 0.006465

Conduct Correlation Test (Test Hypotheses)

cor.test(datasetA$StudyHours, datasetA$ExamScore, method = "spearman")
## Warning in cor.test.default(datasetA$StudyHours, datasetA$ExamScore, method =
## "spearman"): Cannot compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  datasetA$StudyHours and datasetA$ExamScore
## S = 16518, p-value < 2.2e-16
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.9008825

Create a Scatterplot to Visualize the Relationship

ggscatter(
  datasetA,
  x = "StudyHours",
  y = "ExamScore",
  add = "reg.line",
  xlab = "StudyHour",
  ylab = "ExamScore"
)

Report the Results for datasetA Study hours (M = 6.14, SD = 1.37) was correlated with exam score (M = 90.07, SD = 6.80), ρ(98) = .90, p = .000. The relationship was positive and strong. As study hours increased, exam score increased.

Dataset A (StudyHours → ExamScore) — Spearman

Independent variable (StudyHours): M = 6.14, SD = 1.37

Dependent variable (ExamScore): M = 90.07, SD = 6.80

Relationship between variables: There was a relationship between the variables.

Degrees of freedom (df): 98

Correlation value (ρ): 0.90

Exact p-value: p = 0.00000000000000022

Direction & strength: The relationship was positive and strong.

Direction sentence: As study hours increased, exam score increased.

datasetB

Calculate the Descriptive Statistics for datasetB

mean(datasetB$ScreenTime)
## [1] 5.063296
sd(datasetB$ScreenTime)
## [1] 2.056833
mean(datasetB$SleepingHours)
## [1] 6.938459
sd(datasetB$SleepingHours)
## [1] 1.351332

Create Histograms & Visually Check Normality for datasetB

hist(datasetB$ScreenTime,
     main = "ScreenTime",
     breaks = 10,
     col = "red",
     border = "white",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

hist(datasetB$SleepingHours,
     main = "SleepingHours",
     breaks = 10,
     col = "green",
     border = "white",
     cex.main = 1,
     cex.axis = 1,
     cex.lab = 1)

Statistically Test Normality for datasetB

shapiro.test(datasetB$ScreenTime) 
## 
##  Shapiro-Wilk normality test
## 
## data:  datasetB$ScreenTime
## W = 0.90278, p-value = 1.914e-06
shapiro.test(datasetB$SleepingHours)
## 
##  Shapiro-Wilk normality test
## 
## data:  datasetB$SleepingHours
## W = 0.98467, p-value = 0.3004

Conduct Correlation Test (Test Hypotheses) for datasetB

cor.test(datasetB$ScreenTime, datasetB$SleepingHours, method = "spearman")
## 
##  Spearman's rank correlation rho
## 
## data:  datasetB$ScreenTime and datasetB$SleepingHours
## S = 259052, p-value = 3.521e-09
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##        rho 
## -0.5544674

Create a Scatterplot to Visualize the Relationship for datasetb

ggscatter(
  datasetB,
  x = "ScreenTime",
  y = "SleepingHours",
  add = "reg.line",
  xlab = "ScreenTime",
  ylab = "SleepingHours"
)

Report the Results for datasetB Screen time (M = 5.06, SD = 2.05) was correlated with sleeping hours (M = 6.94, SD = 1.35), ρ(98) = -.55, p = .000. The relationship was negative and strong. As screen time increased, sleeping hours decreased.

Dataset B (ScreenTime → SleepingHours) — Spearman

Independent variable (ScreenTime): M = 5.06, SD = 2.06

Dependent variable (SleepingHours): M = 6.94, SD = 1.35

Relationship between variables: There was a relationship between the variables.

Degrees of freedom (df): 98

Correlation value (ρ): -0.55

Exact p-value: p = 0.000000003521

Direction & strength: The relationship was negative and strong.

Direction sentence: As screen time increased, sleeping hours decreased.