While working on model building using Logistic Regression, we did two different ways.

  • Method 1: Created dummy variables before treating missing values. This resulted in 37 columns expanding to 192 columns.
  • Method 2: Treated missing values first followed by dummy variable creation. This resulted in 119 columns.

Which one is preferred and why?

  • $\begingroup$ No easy answer, whatever works best for your end objective. $\endgroup$ Apr 9 at 12:44

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.