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

Re: st: 'xtgee' for logistic regression


From   "Sarah A. Mustillo" <[email protected]>
To   [email protected]
Subject   Re: st: 'xtgee' for logistic regression
Date   Mon, 19 Jul 2004 11:09:47 -0400

Nora -

Do you have time-series data? Just from what you've said, I'm guessing a GEE model might not be your best option for what you are trying to do.

The logistic command does have a cluster option. So, you could do:

logistic dep_var indep_var, cluster(famvar)

If this doesn't help, write back with more details about what you are trying to model.

Sarah

Nora Ghaemi wrote:


dear statalisters,

i have to run a logistic regression that has to take into account clustering of subjects into families.
the command 'logistic' works but does not account for clustering, so the standard errors are smaller that they should be.

i am trying to use on the same dataset the command xtgee:

xtgee dep_var indep_var, family(binomial) link(logit) i(id)


but invariably i get this response from stata:

estimates diverging (absolute correlation > 1)
r(430);


should I rearrange the data somehow in order to run ‘xtgee’? it was my understanding that xtgee does not need to ‘tsset’

can anyone help me with this issue?

thanks a lot!

nora

_________________________________________________________________
Planning a family vacation? Check out the MSN Family Travel guide! http://dollar.msn.com

*
* 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/

--
Sarah A. Mustillo, Ph.D
Department of Psychiatry and Behavioral Sciences
Duke University School of Medicine
Box 3454
Durham NC 27710

919 687-4686 x231
*
*   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 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index