Re: st: poisson - bootstrapping or clustering?

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

At 09:05 AM 9/12/2006, Stas Kolenikov wrote:
> Trying out different seeds is kinda cheating -- it is like you run a
> hundred regressions and pick the one you liked best :)). The actual
> problems might be twofold:
It would be cheating if he kept on changing the seed until the 
coefficients came out the way he wanted!  I am not sure it is 
cheating if you tweak things just to get the models to converge.

Another possibility might be to change the maximization options, e.g. 
add the -difficult- option.  This sometimes helps when models aren't 
converging.

I am curious why the problem occurs in the first place.  I checked 
the Statalist archives, and saw that other people had reported 
similar problems, but Stas is the first person I've seen who offered 
some sort of diagnosis.  I wonder if the error message is deceptive 
in this case; it doesn't make much sense to say there are no cases, 
although that might be a consequence of some other error.


-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
FAX:    (574)288-4373
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu
WWW (personal):    http://www.nd.edu/~rwilliam
WWW (department):    http://www.nd.edu/~soc 
*
*   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/