15. The data listed in “Review Problem 15” (see website: www.wiley.com/college/gupta/

statistics2e) contain data from 252 people reported in “Generalized body composition prediction equation for men using simple measurement techniques” by Penrose et al.

(1985). The variables listed in the original data include: “Percent of body fat index

(BFI),” “Age (years),” “Weight (lbs),” “Height (inches),” “Neck circumference (cm),”

“Chest circumference (cm),” “Abdomen circumference (cm),” “Hip circumference

(cm),” “Thigh circumference (cm),” “Knee circumference (cm),” “Ankle circumference

(cm),” “Biceps (extended) circumference (cm),” “Forearm circumference (cm),”

and “Wrist circumference (cm).” For learning propose, we dichotomize the percent of body fat index into a new variable name “Index.”

(a) Construct a classification tree using all the variables except “Percent of body fat index” to predict the “Index.”

(b) Discuss the quality of the fitted model in part

(a) using the confusion matrix.

(c) Construct a regression tree using all the variables except “Index” to predict “Percent of body fat index.”

(d) Evaluate the quality of the prediction using a suitable method.