Statalist


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

st: AW: "Estimates diverging" error message in -xtlogit, pa-


From   "Martin Weiss" <martin.weiss1@gmx.de>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: AW: "Estimates diverging" error message in -xtlogit, pa-
Date   Wed, 21 Oct 2009 15:50:43 +0200

<> 

If anyone wants to reproduce Thomas` problem:


*************
webuse union, clear
xtdes

set seed 76843
replace union=. if runiform()<.8
xtdes

xtlogit union age grade  /* 
*/ i.not_smsa south##c.year, /* 
*/ pa cor(unst)
*************



HTH
Martin


-----Ursprüngliche Nachricht-----
Von: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] Im Auftrag von Thomas Klausch
Gesendet: Mittwoch, 21. Oktober 2009 15:39
An: statalist@hsphsun2.harvard.edu
Betreff: st: "Estimates diverging" error message in -xtlogit, pa-

Dear list members,

When estimating a population averaged (marginal) model with -xtlogit,
pa- I receive the error message "estimates diverging (missing
predictions)". This happens only if I use an unstructured correlation
structure.

I am analysing unbalanced panel data with missing observations for
many individuals. I suppose this could be an explanation. What,
however, would be a suitable solution, switching to an exchangeable
structure? Or shouldn't I use marginal models in unbalanced panels?

Thanks
Thomas
*
*   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