2. In this question, you will perform model selection using the College data set in ISLR library. An explanation of the variables in this data set is included in the Appendix to this assignment. Our goal is to predict the number of applications as a function ofthe other variables. 3) Using the best subset selection method, what is the best model according to CF, criterion? State the predictors in the best model and their coefficients. Hint: First, use regsubsets O to determine the best model with k predictors for k = 1, 2, ..., 1? {because we can have at most 17 predictors in this data). Then, compare the CI: of the best model with 1 predictor versus the CD of the best model with 2 predictors versus the (2,, of the best model with 13' predictors. {For guidance, check how we made similar comparisons for Hitters data set in class.) The model with the lowest (2,, is the best model. b) Repeat part la) using the Bayesian Information Criterion (BIC) to rank models. State the predictors in the best model and their coefficients. c) Are the models in part (a) and lb) the same? If not, explain why one has fewer predictors than the other. d) Using the forward stepwise selection method, what would be the best model with 10 predictors? {State the predictors included in the model and their coefficients.)