Consider the accompanying data to analyze how people view divorce (Acceptable equals 1 if morally acceptable, 0 otherwise) on the basis of age and religiosity (Religious equals 1 if very religious, 0 otherwise). 

a. Use the holdout method to compare the accuracy rates of two competing logistic models for divorce, using the first 150 observations for training and the remaining 50 observations for validation. Model 1 uses Age and Religious as predictor variables, whereas Model 2 also incudes the interaction between Age and Religious. 

b. Use the k-fold cross-validation method to compare the accuracy of the models using k = 4.