Bookmark and Share

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

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

Re: st: Are my -xtmixed- intercepts accurate?

From   "Clyde Schechter" <>
Subject   Re: st: Are my -xtmixed- intercepts accurate?
Date   Sat, 21 Aug 2010 16:21:39 -0700


One side comment unrelated to the interpretation of the residuals.

If I understood the original post correctly, you want to contrast the
change over time between treatment groups.  In that case, your model
should have a time X tx interaction term among the fixed effects.  So,
assuming time is a discrete variable in your situation, I think it should
look like:

xtmixed avg i.time##i.tx || ...

Clyde Schechter, MA MD
Associate Professor of Family & Social Medicine

Please note new e-mail address:

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index