If a model doesn't converge I always start with simpler models and add
step by step random effects, interactions, etc. This usually enables me
to find the problem. (usually its me...)
Hope this helps,
Maarten
--- Ashutosh Patil <[email protected]> wrote:
> Hello Folks:
>
> I am running xtmixed with a 3-level design. I am looking for the
> significance of cross-level effects, and also for significance of
> fixed
> and random coefficients.
>
> I am running this on Stata 9.2 (with all the latest updates). I read
> on
> http://www.stata.com/help.cgi?whatsnew that this problem of "hessian
> becoming unstable and/or assymmetric" has been overcome in the latest
> Stata update.
>
> However, with ML (and reml), the program ends and it does provide me
> the
> output. However, there are two warning messages in red. The first is,
> "Hessian has become unstable or asymmetric". And, the second is,
> "Warning:
> convergence not achieved; estimates are based on iterated EM".
>
> What do I conclude with this. Is there any ill-conditioning of the
> data?
> Or, is this bug in Stata?
>
> Any advice will be greatly appreciated.
>
> Thanks,
> Ash
>
>
>
>
____________________________________________________________________________________
> Be a PS3 game guru.
> Get your game face on with the latest PS3 news and previews at Yahoo!
> Games.
> http://videogames.yahoo.com/platform?platform=120121
> *
> * 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/
>
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
___________________________________________________________
Now you can scan emails quickly with a reading pane. Get the new Yahoo! Mail. http://uk.docs.yahoo.com/nowyoucan.html
*
* 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/
