Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: statistical test for interactions in svyregress models


From   Michelle Garrison <garrison@u.washington.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: statistical test for interactions in svyregress models
Date   Tue, 19 Apr 2005 17:28:36 -0700

Hi -- I'm looking for a way to statistically test for interactions (effect modification) in a svyregress model. If I was just using regress, I'd just use lrtest to compare nested models with and without the interaction terms -- but since lrtest can't be used with svy commands, I'm not sure how to go about this. Is there a way in stata to get this information from a Wald test?

If it makes a difference, the interaction of interest is between a categorical variable with 3 values (race) and an ordered variable with 4. Race also happens to be the one that the survey weights are based on.

Comparing the results of regressions stratified by race, it seems pretty clear that interaction is occuring, but we'd like to have a statistical test we can cite as saying so.

Thanks in advance for any help people have!


--
___________________________________________________

Michelle Garrison, M.P.H. -- Research Consultant
Child Health Institute, University of Washington
office: (206) 616-1203 fax: (206) 616-4623
campus mailbox 354920
e-mail: garrison@u.washington.edu ___________________________________________________

*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* 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   |   What's new   |   Site index