Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "Özlen D. Luznar" <ozlend1@umbc.edu> |
To | statalist@hsphsun2.harvard.edu |
Subject | st: Interacting dummies and multicollinearity issue |
Date | Wed, 23 Jun 2010 07:50:40 -0400 (EDT) |
Hi everyone, I am using a recursive biprobit model. I have 2 separate categorical variables. variable d - has 3 values - dummied out to d1 d2 d3 variable e has 4 values dummied out to e1 e2 e3 e4 In addition to include d1 d2 e1 e2 e3 in my model I want to include interaction terms between d dummies and e dummies: 12 possible variables interaction between d dummies and e dummies. Among these 12 I know that at least 3 dummies have only one value and that is 0, in other words d2*e2 == 0 for everyone, d3*e1 == 0 for everyone and d2*e1==0 for everyone. I am confused as to which of these 12 I can/should include in the model so as to avoide multicollinearity. This may be a basic question but I appreciate any help you may give me. Thanks! Ozlen -- Özlen D. Luznar PhD Candidate - Public Policy Graduate Research Assistant University of Maryland Baltimore County (UMBC) 1000 Hilltop Circle Baltimore, MD 21250 443-846-5010 * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/