Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


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

Re: st: initial values not feasible


From   Nick Cox <njcoxstata@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: initial values not feasible
Date   Sun, 2 Dec 2012 18:11:45 +0000

-xtmpg- is from SJ 7-2. Please remember...

I am not clear what kind of help you expect us to be able to give.
Perhaps the parameter estimates for the model that converged would be
reasonable starting points for trying again with  the model that
didn't. Either way, your possibilities clearly range from trying
non-default starting values to concluding that the first model is
inappropriate for your data.

There is little white magic with such models. They're always written
up with examples that work well -- I've done precisely the same in
other territories -- but they won't work if the generating process is
something different. Often one needs to take a hard look at how many
parameters are being estimated with how much data (how many panels,
how long).

Nick

On Sun, Dec 2, 2012 at 6:01 PM, urbain thierry YOGO <yogout@gmail.com> wrote

> I am trying to run a pooling mean group estimation using xtpmg. My
> equation looks like this:
> xtpmg d.ltgdp d.(ldep lrev dte), ec(ec) lr( ldep lrev dte), pmg replace
> however stata gives me back the error 1400 "initial values not feasible).
> But whent i run the model only with the first two variables (ltgdp
> ldep) stata gives me the right output.
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index