Introduction
The dataset is from R preloaded libraries and it consists of speed / distance values.
library(ggplot2)
df<-get("cars")
df
Correlation coefficient provides us the relationship between the variables. If it is greater then a strong relationship exists and if it is low then the relationship is weak or none.
cor_df<-cor(df$speed, df$dist)
cor_df
## [1] 0.8068949
The Correlation coefficient is ~ 0.8 and this shows speed has strong impact over stopping distance.
lm_speed <- lm(dist ~ speed, data = df)
lm_speed
##
## Call:
## lm(formula = dist ~ speed, data = df)
##
## Coefficients:
## (Intercept) speed
## -17.579 3.932
summary(lm_speed)
##
## Call:
## lm(formula = dist ~ speed, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -29.069 -9.525 -2.272 9.215 43.201
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -17.5791 6.7584 -2.601 0.0123 *
## speed 3.9324 0.4155 9.464 1.49e-12 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 15.38 on 48 degrees of freedom
## Multiple R-squared: 0.6511, Adjusted R-squared: 0.6438
## F-statistic: 89.57 on 1 and 48 DF, p-value: 1.49e-12
ggplot(data = df, aes(x = speed, y = dist)) +
geom_point(color='blue') +
geom_smooth(method = "lm", se = FALSE)
It is necessary to plot residuals and see if there are any variances.
hist(lm_speed$residuals)
qqnorm(lm_speed$residuals)
qqline(lm_speed$residuals)
plot(lm_speed$residuals ~ df$dist)
par(mfrow=c(2,2))
plot(lm_speed)
We can conclude by saying that the data satisfies the conditions of linear model. Below are explanations.
Linearity - The data is linear as the residuals are following theoretical line.
Homoscedasticity - From Scale location plot we can see that the line is horizontal and not angled. This explains the homoscedasticity is satisfied.
Independence - Speed and Stopping distance are both independent variables
Normality - By looking at the QQ Plot we can see that the data is distributed normally