we will now try to predict the per capita crime rate in the boston data set, which is part of the mass package. (a) use at least 3 of the 4 different model selection and regularization methods dis- cussed in class (lectures 11, 14, 15): best subset selection, pcr, ridge regression, and the lasso. present and discuss your results. (b) propose a model that seems to perform well on this data set, and justify your answer. make sure that you define which criterion you are using to evaluate model performance. (c) does your chosen model involve all of the features in the data set? why or why not?