Try changing the algorithm to Newton and/or tighten up the convergence criteria.
If you use the Stata data set for -zip-,
webuse fish
zip count live person ,inflate(camp child)
you will not get the same results in Limdep with the default settings
(POISSON;Lhs=COUNT;Rhs=ONE,LIVEBAIT,PERSONS;ZIP;Rh2=ONE,CAMPER,CHILD$).
However if you change the algorithm and the number of iterations to:
POISSON;Lhs=COUNT;Rhs=ONE,LIVEBAIT,PERSONS;ZIP;Rh2=ONE,CAMPER,CHILD;Alg=N
;Maxit=1000$
the results will be the same.
Hope this helps,
Scott
----- Original Message -----
From: "Javier Gonzalez" <[email protected]>
To: <[email protected]>
Sent: Saturday, January 17, 2004 8:47 AM
Subject: st: results
> I am trying to fit a ZIP model using STATA and compared it to the results I
> achieved with LIMDEP. The results were considerably different. Does anyone
> know why? Or offer suggestions.
>
> thanks
*
* 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/
