Based on domain knowledge and preliminary variable selection, we have decided a set of 10 variables as predictor variables for building regression models. What are the general approaches to identify the interaction terms from these 10 variables. It seem that it is not a good idea to build interaction terms in a combinatorial way. Any suggestions will be highly appreciated.
Asked
Active
Viewed 257 times
1
-
SO is a coding site. CrossValidated is the statistical questions site. – DWin Nov 13 '14 at 20:36
-
I suggest you first search CV.com with the words in your the title of your question. – DWin Nov 13 '14 at 21:03