3. Try to fit an MLR to this dataset, with MEDV as the dependent variable. Keep the first 350 records as a training set (call it Bos_train) which you will use to fit the model; the remaining 156 will be used as a test set (Bos_test). Use only the following variables in your model: LMEDV -LSTAT + RM + CRIM + ZN + CHAS 4. Report the coefficients obtained by your model. Would you drop any of the variables used in your model (based on the t-scores or p-values)? 5. Report the MSE obtained on Bos_train. How much does this increase when you score your model (i.e., predict) on Bos_test? 6. (Bonus 1 point). Use the stepwise regression to reach your final model. Try different model section criteria (i.e., AIC, BIC, adj R^2) and see if you can come up with the same model even with the different criteria. Determine the best model if you get different models with different criteria. Consider a model that gives the highest accuracy (in terms of MSE) in the test set as the best model