Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

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

Re: st: gllamm estimates

From   Wassim Tarraf <>
Subject   Re: st: gllamm estimates
Date   Thu, 11 Nov 2010 19:51:10 -0500

Thanks Stas! The problem went away after I reinstalled gllamm.

On 11/11/2010 4:42 PM, Stas Kolenikov wrote:
Apparently something went wrong in comprob3, which is not an official
Stata command. It is probably a part of -gllamm-. If you want to
bother and track the error down, you would want to -set trace on- and
see where -gllamm- hits that non-existent variable. There may be a
minor bug in -gllamm-, or you might have mismatching versions of
different components of -gllamm-. I would start by downloading the
most recent version and see if the error still shows up.

On Thu, Nov 11, 2010 at 2:48 PM, Wassim Tarraf<>  wrote:
Dear list members,

I am using Rabe-Hesketh, Pickles and Skrondal's "gllamm" (reference below)
in Stata 11.1 to estimate a random effects model. Storing/saving the
estimates works fine (no error messages) but when attempting to restore them
I get the following error message: "variable __00000M not found something
went wrong in comprob3". I would appreciate your guidance on what could have
went wrong and how to fix it (if possible) .

Rabe-Hesketh, S., Pickles, A. and Skrondal, S. (2004). GLLAMM Manual. U.C.
Berkeley Division of Biostatistics Working Paper Series. Working Paper 160.

*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index