Consider the following portion of data that includes information about home loan applications. Variables on each application include the application number (Application), whether the application is conventional or subsidized by the federal housing administration (LoanType), whether the property is a single-family or multifamily home (PropertyType), and whether the application is for a first-time purchase or refinancing (Purpose).

a. Are the variables LoanType, PropertyType, and Purpose nominal or ordinal data? Why?

b. Which categories are the most frequent categories for LoanType, PropertyType, and Purpose? 

c. To facilitate subsequent analyses, transform LoanType, PropertyType, and Purpose into dummy variables. Use the most frequent categories of the variables as the reference categories. Which categories of LoanType, PropertyType, and Purpose are the reference categories? How many dummy variables are created in total? 

Transcribed Image Text:

Application 1 2 B 103 LoanType Conventional Conventional ⠀ Federal Housing PropertyType Purpose Single-family Purchase Multi-family Refinancing ⠀ B Single-family Purchase