Statalist


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

st: GEE with weights for MAR dropout


From   "Tomas Lind" <tomas.lind@ki.se>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: GEE with weights for MAR dropout
Date   Thu, 17 Sep 2009 11:42:25 +0200

Dear Listers,

Weighted GEE for a longitudinal study with five observations and a binary
outcome

The GEE method for analysing longitudinal data assumes that dropouts are
MCAR. However, I have read somewhere that there is a modified weighted GEE
that can handle MAR-data. Does anyone know how to do this in Stata. 

(Another option would be to analyze data with a mixed (random) effects
model. However a mixed effect model would produce subject specific
parameters why these results would not be comparable with results from a
GEE-model that have been reported by others. It would also be nice to
compare the results from the ordinary GEE and the weighted GEE in our field
of work.) 
 

/Tomas

*
*   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