Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: robust cluster in GLM


From   Steven Samuels <sjhsamuels@earthlink.net>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: robust cluster in GLM
Date   Tue, 16 Sep 2008 16:27:31 -0400

-

Leny, "standard error" of what? Please follow the Statalist FAQ (section 3.3) and "Say exactly what you typed and exactly what Stata typed (or did) in response. N.B. exactly!" Are the time-points equally spaced? If so, and you are estimating the slope, then the middle time point would be ignored.

-Steve


On Sep 16, 2008, at 3:46 PM, Leny Mathew wrote:


Dear Statalisters,
                          I'm using a GLM model with robust cluster
option to model longitudinal data across three time points. I have the
dependent variable on 80 cases at T1 and T2, but have only 77 at the
third time point. When I run the model the number of observations is
237, but it says that the standard error is adjusted for 80 clusters.
Why would this be the case? How does stata take the missing info for
the 3 people at T3 into consideration when it calculates the
parameters and SE?

Thanks in advance for any suggestions,

Leny
*
*   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/
*
*   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   |   What's new   |   Site index