cor.test(data$wt,data$mpg) # to find the correlation value
# simple linear regression
slr = lm(mpg~wt, data)
summary(slr)
plot(slr$resid) # Residual plot
qqnorm(slr$resid) #Q-Q Plot
# Multiple linear regression
mlr = lm(mpg~wt+gear, data)
summary(mlr)
plot(mlr$resid) # Residual plot
qqnorm(mlr$resid) #Q-Q Plot
EXPLANATION
This is a code written in R programming language to perform exploratory data
analysis and regression analysis on a dataset of cars. Here is a brief explanation of each line of the code:
1. rm(list=ls()): This line removes all objects in the current R environment.
2. data <- mtcars: This line loads the mtcars dataset into the data variable. 3. library(dplyr): This line loads the dplyr package, which provides functions for data manipulation. 4. data <- sample_n(data, 15): This line randomly selects 15 rows from the data dataset. 5. library("ggplot2"): This line loads the ggplot2 package, which provides functions for data visualization. 6. ggplot(data, aes(x=wt, y=mpg)) + geom_point(): This line creates a scatter plot of mpg versus wt variables in the data dataset. 7. cor.test(data$wt, data$mpg): This line calculates the correlation coefficient between wt and mpg variables in the data dataset. 8. slr <- lm(mpg ~ wt, data): This line fits a simple linear regression model of mpg on wt variable in the data dataset. 9. summary(slr): This line displays the summary statistics of the slr model. 10. plot(slr$resid): This line creates a residual plot of the slr model. 11. qqnorm(slr$resid): This line creates a Q-Q plot of the slr model. 12. mlr <- lm(mpg ~ wt + gear, data): This line fits a multiple linear regression model of mpg on wt and gear variables in the data dataset. 13. summary(mlr): This line displays the summary statistics of the mlr model. 14. `plot(mlr$resid)