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

st: RE: Problem with xtmixed after gam (was:xtmixed broken in Stata 9.1?)


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: Problem with xtmixed after gam (was:xtmixed broken in Stata 9.1?)
Date   Wed, 21 Sep 2005 22:05:15 +0100

Patrick Royston has not been a member of Statalist
for some years. I doubt that your guess is precisely 
in the right territory, particularly in terms of 
what a Fortran program might do here. 

Perhaps you could try other solutions such as

. estimates clear 

before firing up 

. xtmixed 

again. 

Nick 
n.j.cox@durham.ac.uk 

Dr. Stephen Rothenberg
 
> The problem was solved by exiting Stata, shutting down the 
> machine, booting 
> up cold and re-running the commands.
> 
> Previous to the xtmixed problems I had been running a set of 
> -gam- models on 
> another data set.
> 
> After successfully running -xtmixed- on a clean machine and 
> unused Stata 
> session, I then tried a -gam- analysis and went back to 
> -xtmixed-.  The 
> problem re-appeared.
> 
> Apparently -gam- now does something bad to Stata 9.1, leaving 
> it in a state 
> from which it cannot use what -xtmixed requires.  Perhaps its 
> call to a 
> FORTRAN program is what screws up the subsequent -xtmixed-.  
> The problem 
> doesn't occur after -gam- when I run the "pig" data set with 
> regress nor 
> when I try -xtreg, mle-, but I don't have time to 
> exhaustively test all 
> the -xt- commands
> 
> Does anyone know if Patrick Royston or Gareth Ambler, the 
> authors of -gam-, 
> are still members of statalist?
> 
> Thanks for clueing me that it was something I had done, Nick, and not 
> general to Stata 9.1.
> 
> Best,
> Steve
> 
> ----- Original Message ----- 
> From: "Nick Cox" <n.j.cox@durham.ac.uk>
> To: <statalist@hsphsun2.harvard.edu>
> Sent: Wednesday, September 21, 2005 3:08 PM
> Subject: st: RE: Re: RE: xtmixed broken in Stata 9.1?
> 
> 
> > That clearly looks OK. The explanation
> > must therefore lie elsewhere, but I've
> > run out of ideas.
> >
> > Nick
> > n.j.cox@durham.ac.uk
> >
> > Dr. Stephen Rothenberg
> >
> >> Here is my update status:
> >>
> >> --------------------------------------------------------------
> >> -------------------
> >> update query
> >> --------------------------------------------------------------
> >> -------------------
> >> (contacting http://www.stata.com)
> >>
> >> Stata executable
> >>     folder:               C:\Program Files\Stata9\
> >>     name of file:         wsestata.exe
> >>     currently installed:  15 Sep 2005
> >>     latest available:     15 Sep 2005
> >>
> >> Ado-file updates
> >>     folder:               C:\Program Files\Stata9\ado\updates\
> >>     names of files:       (various)
> >>     currently installed:  19 Sep 2005
> >>     latest available:     19 Sep 2005
> >>
> >> Recommendation
> >>     Do nothing; all files up to date.
> >>
> >> Click to edit automatic update checking preferences
> >> --------------------------------------------------------------
> >
> > Nick Cox
> >
> >> > This works for me.
> >> >
> >> > Perhaps you updated your executable, but not
> >> > the other files.
> >
> > Dr. Stephen Rothenberg
> >
> >> >> I'm trying to run -xtmixed- in Stata 9.1 SE, Windows XP,
> >> >> after successfully using it in Stata 9.0.
> >> >>
> >> >> I keep getting the same error message no matter what my model
> >> >> specs are (see
> >> >> below).  Finally I tried copying Example 1 from the -xtmixed-
> >> >> section of the
> >> >> panel data manual.
> >> >>
> >> >> I downloaded the "pig" data set used in the example and tried
> >> >> the code
> >> >> listed there:
> >> >>
> >> >>     . use http://www.stata-press.com/data/r9/pig
> >> >>     (Longitudinal analysis of pig weights)
> >> >>
> >> >>     . xtmixed weight week || id:
> >> >>     last estimates not found
> >> >>     r(301);
> >> >>
> >> >> The "not found" error message is the same problem when I use
> >> >> my own data
> >> >> set.
> >> >>
> >> >> Am I doing something dumb or is -xtmixed- broked in Stata 9.1?
> >
> > *
> > *   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/
> >
> > 
> 
> 
> *
> *   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/
> 

*
*   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index