Suppose that you take a data set and divide it into two parts of equal size. The first part (Part I) and the second part (Part II). You will try out two different classification procedures, by using Part I and Part II as you training set and test set, respectively. Which means that you will use half of the data for training, and the remaining half for testing. a) First we use 1-Nearest Neighbour rule (1-NN) and get an average error rate (averaged over both test and training data sets) of 8%. What was the error rate with 1-nearest neighbour on the test set? Briefly reason the answer. b) Next we use the Adaboost Algorithm and get an error rate of 10% on the training data. We also get the average error rate (averaged over both test and training data sets) of 12%. What was the error rate with the Adaboost Algorithm on the test set? Just answer the error rate. c) Now, we swap the roles of Part I and Part II, and repeat the same experiments. On the test set (Part I), we get an error rate of 12% with both 1-NN and the Adaboost Algorithm. Based on all these results, by the cross-validation, indicate the method which we should prefer to use for classification of new observations, with a simple tivate W reasoning. Go to Setting