R Markdown
# Load the dataset
df <- read.csv(file.choose(), header = TRUE)
attach(df)
dim(df)
## [1] 200 4
# Summary statistics
summary(df)
## TV Radio Newspaper Sales
## Min. : 0.70 Min. : 0.000 Min. : 0.30 Min. : 1.60
## 1st Qu.: 74.38 1st Qu.: 9.975 1st Qu.: 12.75 1st Qu.:11.00
## Median :149.75 Median :22.900 Median : 25.75 Median :16.00
## Mean :147.04 Mean :23.264 Mean : 30.55 Mean :15.13
## 3rd Qu.:218.82 3rd Qu.:36.525 3rd Qu.: 45.10 3rd Qu.:19.05
## Max. :296.40 Max. :49.600 Max. :114.00 Max. :27.00
plot(TV, Sales, col = 'red', pch = 16)
hist(TV, border = 'black', col= 'white')
hist(Sales, border = 'black', col = 'white')
boxplot(TV, border = 'black', col='gray')
boxplot(Sales, border = 'black', col ='gray')
model <-lm(Sales~TV)
summary(model)
##
## Call:
## lm(formula = Sales ~ TV)
##
## Residuals:
## Min 1Q Median 3Q Max
## -6.4438 -1.4857 0.0218 1.5042 5.6932
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.974821 0.322553 21.62 <2e-16 ***
## TV 0.055465 0.001896 29.26 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.296 on 198 degrees of freedom
## Multiple R-squared: 0.8122, Adjusted R-squared: 0.8112
## F-statistic: 856.2 on 1 and 198 DF, p-value: < 2.2e-16
plot(model)
boxplot(residuals(model))
confint(model)
## 2.5 % 97.5 %
## (Intercept) 6.33874038 7.61090260
## TV 0.05172671 0.05920283
coef(model)
## (Intercept) TV
## 6.97482149 0.05546477