Answer True or False.If your answer is False, explain why it is False.

a. Multicollinearity results when the regressors are highly correlated with the response variable. b. If All Possible Regression results are available then Stepwise Procedure results are not needed. C. If VIF(X1) is large then R^2 obtained from regressing X1 on the other X's is close to 0. d. If a Regression Model includes X1, X2,. .., X5 with X'X diagonal then a forward selection and a backward elimination, where both procedures are based on AIC, always result in the same final model. e. For a multiple regression, the log transformation of the response variable is a possible technique that can be used to reduce the impact of multicollinearity. f. A model with a low R^2 should not be used for prediction purposes. g. The goal of cross-validation is to simulate the test data set error. h. If a model has a low training set error and a high test set error then the model is likely to overfit. i. We can fix overfitting by either using a less complex model or removing X's. j. Adding data to the test data set can remedy overfitting