Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: interactions for xtmelogit models


From   rgutierrez@stata.com (Roberto G. Gutierrez, StataCorp)
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: interactions for xtmelogit models
Date   Tue, 23 Feb 2010 14:12:19 -0600

Dale Hardy <Dale.S.Hardy@uth.tmc.edu> asks:

> A few months age I asked you a question about xemelogit interaction and you
> send me the link below.

> On page 15/36 of the presentation by Gutierrez entitled, Â?Tricks of the
> trade: getting the most out of xtmixedÂ?, is a model for xtmixed
> interaction.

> My question is:  Why isn't age not in the model? Age is with the interaction
> terms but not as a single term. Would that make the model not hierarchally
> well-formed?

The variable -age- is in the model, it's just that it is coded as two
interactions of complimentary binary variables with age, rather than as one
main effect and one dummy interaction.  That is, instead of the standard

   . xtmixed ... age ageXgirl ...

You have 

   . xtmixed ... ageXboy ageXgirl ...

The model is the same in both, but the latter coding is used to match what was
used in the random part of the model, where such a coding makes interpretation
easier -- you have one set of variance components for boys and one for girls.

--Bobby
rgutierrez@stata.com
*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index