Q4. The goal of this question is predicting breast cancer based on the characteristics of the cell nuclei present in medical images. In the homework package, you can access the data file "CancerData.cav", which consists of 30 features and one response variable (diagnosis). Below we summarize a brief description of each feature: Diagnosis (the response variable): M = malignant, B = benign, radius (mean of distances from center to points on the perimeter) texture (standard deviation of gray-scale values) perimeter area smoothness (local variation in radius lengths) compactness (perimeter / area - 1.0) concavity (severity of concave portions of the contour) concave points (number of concave portions of the contour) symmetry fractal dimension ("coastline approximation" - 1) The mean, standard error and "worst" or largest (mean of the three largest values) of these features were computed for each image, resulting in 30 features. For instance, field 3 is Mean Radius, field 13 is Radius SE, field 23 is Worst Radius. (a) Consider splitting the data into a a training and test set. Samples 1 to 450 form the training set and samples 451 to 569 form the test set. Try the following classification models to predict "diagnosis" in terms of the other features in the dataset: Use logistic regression for your classification. Report the p-values associated with the intercept and all the features. Which features have large p-values? Use the test data to estimate the accuracy of your model. Apply LDA and QDA, and again report your model accuracies using the test data