Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Gordon Hughes <G.A.Hughes@ed.ac.uk> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: a question about gologit2 mlogit and ologit |
Date | Mon, 24 Jun 2013 13:13:14 +0100 |
Mr Zhang,Please have some consideration for other contributors to Statalist. First, people are not just waiting to answer your question - especially not on a weekend. Second, think more carefully about what you want to ask before sending message.
The procedure -gologit2- is user-written, while the -mlogit- and -ologit- procedures are part of Stata. Hence the syntax of the procedures may differ, which will affect the use of factorial notation. You don't say whether your variables a and b are categorical or continuous. These and other considerations will affect the answer to your question.
The simplest response is that you should create your own interactions and test them in your model. I have no idea whether this would make statistical or any other kind of sense, but you have not provided sufficient information to go any further.
Gordon Hughes g.a.hughes@ed.ac.uk * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/