Refer again to the example referenced in Exercise 7 and its program using alternating stepwise selection. Run the alternating stepwise selection code using k = 0.
(a) Notice that all variables are in the final model. Why must this happen?
(b) In the final model, the variables are in order relative to how much IC(0) would change if the variable were dropped. Notice that this is not the same as the order in which the variables were entered. Explain why this can happen.
Exercise 7
Section 5.1.4 includes an example involving the placekicking data set and alternating stepwise selection of its variables for a logistic regression model. Run the alternating stepwise selection program referred to in the example and report the results. For the final model, compute how much BIC would increase with each possible change that could be made to the model.