Re: st: xtpois still maximizing after 1200 iterations

[Richard Williams <Richard.A.Williams.5@ND.Edu>]

At 08:53 AM 10/14/2005, Scott Cunningham wrote:
> I'm regressing non-negative integer (# of recent partners in last
> twelve months) onto a few covariates, but only when I include the
> year dummies (i.year) does xtpois have trouble reaching a maximum.
> It appears stuck - after 1200 iterations, it's still going, and it
> seems not to be making any progress.
>
> Can I tell Stata to quit after, say, 2000 iterations or something
> like that?  Or should I interpret the failure to maximize with  more
> caution and try something different?  Is there an algorhthm I could
> use that will make it step to the max easier - like BHHH or something
> like that?
>
> Any help is much appreciated.
Type -help maximize- and pay particular attention to the -difficult- 
, -iterate- and -technique- options.  My troubleshooting FAQ for 
-gologit2- discusses these options but I think much the same advice 
would apply to lots of routines.  See

http://www.nd.edu/~rwilliam/gologit2/tsfaq.html

See the section entitled "gologit2 is very slow and/or does not converge".

Incidentally, I'd be interested in other generic, all purpose advice 
for such problems. 
*
*   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/