Whenever I use the -adapt- subcommand in GLLAMM the model will not run.
After obtaining initial estimates it writes the following:
start running on 14 Aug 2002 at 08:00:56
1m2 invalid name
finish running on 14 Aug 2002 at 08:00:57
This occurs regardless of the data being used. It also occurs even though
the model runs fine when I do not use the -adapt- subcommand. It would be
great if I could use the -adapt- subcommand because -adapt- is faster, and
on this project models have taken days to run. The model has multiple
random effects, a simple model with 2 random effects failed to run.
FYI, a subset of what I've checked already:
1)I checked the GLLAMM manual and it says adaptive quadrature cannot be
used with the ip(f) or ip(f0) option. I am not using those options.
2)I have also already sent a note to the author of the module (on July 9)
and have not received a reply.
3)I checked and our executable was installed 11 Jun 2002, and ado files
were installed 21 Jun 2002. Although new ado files are available (as of
Aug 9, 2002), I am reluctant to ask the system administrator to update the
ado files without knowing that the particular problem I am encountering
has been addressed.
Any assistance anyone can provide is greatly appreciated.
Thanks.
Sam
*
* 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/
