Programming Problem 2 This question involves the use of multiple lin- ear regression on the Auto data set. 1. Compute the matrix of correlations. (1) Produce a colorplot of the correlation matrix; (2) Display the matrix. You will need to exclude the "name" variable since it is qualitative and not useful here. Which variables are highly correlated? Here we say a pair of variables are highly correlated if their pairwise correlation is above 0.8 (in absolute value). 2. Use least squares to perform a multiple linear regression with "mpg"as the response and all other variables except "name "as the predictors. What are the coefficients and the RSS? 3. Compare the result of multiple linear regression with simple linear regression above. Which one is better