If school ratings can be reasonably well-predicted from the other factors, and new schools built due to recent population growth cannot be reasonably well-classified using the other factors, which model would you recommend?

a. Model 1: Imputation with average school rating from the rest of the data.

b. Model 2: Imputation with a regression model based on other variables.

c. Model 3: Imputation with a classification model to estimate new school purpose and two regression models for rating.

d. Model 4: Binary variable to identify locations with missing information.

e. Model 5: Categorical variable with a classification model for new school purpose and neighborhood categorization.