Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

st: xtgee, margins, and postestimation of odds ratios


From   Chuck Cleland <ccleland@optonline.net>
To   statalist@hsphsun2.harvard.edu
Subject   st: xtgee, margins, and postestimation of odds ratios
Date   Wed, 23 Jan 2013 09:37:50 -0500

xtgee outA cov1 cov2 cov3 c.TIMEU##i.tx, link(logit) corr(unst) family(binomial) robust

I then used margins to describe the outcome for each treatment condition and time point, adjusting for covariates:

margins tx, at(TIMEU=(0 .3333333 .6666667 1))

I would like to get point and interval estimates for odds ratios at each of the four time points (comparing treatment and control). This is the closest thing I know of using margins:

margins r.tx, at(TIMEU=0) at(TIMEU=.3333333) at(TIMEU=.6666667) at(TIMEU=1) contrast(nowald effects)

But the contrast is the risk difference rather than the odds ratio. Does anyone know how to obtain point and interval estimates of odds ratios with margins or some other approach?

Thanks,

Chuck Cleland

--
Chuck Cleland, Ph.D.
NYU College of Nursing
726 Broadway, 10th floor
New York, NY 10003
tel: (212) 992-9417 (Tu, W, Th)
tel: (732) 512-0171 (M, F)

*
*   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/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index