library(tidyverse
)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.3 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
data1 <- read_csv('/Users/souleymanedoumbia/Library/Mobile Documents/com~apple~CloudDocs/CUNY SPS CLASSES/MSDS CLASSES/DATA 605 Spring2024 /Week 11/Discussion board/Exam_data.csv')
## Rows: 100 Columns: 2
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl (2): Hours_Studied, Exam_Score
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
summary(data1)
## Hours_Studied Exam_Score
## Min. :1.050 Min. :12.44
## 1st Qu.:2.739 1st Qu.:24.40
## Median :5.177 Median :34.14
## Mean :5.232 Mean :36.15
## 3rd Qu.:7.572 3rd Qu.:48.02
## Max. :9.882 Max. :63.32
head(data1)
## # A tibble: 6 × 2
## Hours_Studied Exam_Score
## <dbl> <dbl>
## 1 4.37 32.3
## 2 9.56 56.3
## 3 7.59 48.4
## 4 6.39 32.0
## 5 2.40 20.9
## 6 2.40 23.8
#the linear model
model1 <- lm(Exam_Score ~ Hours_Studied, data=data1)
#Summarizing the model to get the coefficients and other statistics
summary(model1)
##
## Call:
## lm(formula = Exam_Score ~ Hours_Studied, data = data1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -9.6371 -3.5937 0.2384 2.3378 11.4653
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 11.3309 0.9997 11.34 <2e-16 ***
## Hours_Studied 4.7446 0.1703 27.86 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 4.536 on 98 degrees of freedom
## Multiple R-squared: 0.8879, Adjusted R-squared: 0.8868
## F-statistic: 776.4 on 1 and 98 DF, p-value: < 2.2e-16
library(car)
## Loading required package: carData
##
## Attaching package: 'car'
## The following object is masked from 'package:dplyr':
##
## recode
## The following object is masked from 'package:purrr':
##
## some
# Checking for linearity and homoscedasticity visually
plot(model1, which=1) # Residuals vs Fitted
plot(model1, which=3) # Scale-Location (also for checking homoscedasticity)
# Residual Analysis
par(mfrow=c(2,2))
plot(model1)
# Normality of residuals
hist(residuals(model1), breaks=10, main="Histogram of Residuals", xlab="Residuals") # Histogram of residuals
shapiro.test(residuals(model1)) # Shapiro-Wilk test for normality
##
## Shapiro-Wilk normality test
##
## data: residuals(model1)
## W = 0.98463, p-value = 0.2984
# Independence of residuals
durbinWatsonTest(model1)
## lag Autocorrelation D-W Statistic p-value
## 1 -0.145225 2.284998 0.158
## Alternative hypothesis: rho != 0
It seems like the linear model is quite appropriate given the high R-squared and the significant predictor variable.