Re: st: offset in zip regression model

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

At 08:35 AM 7/30/2008, Jen Rose wrote:
> Hi,
>
> I'm wondering if anyone can tell me the correct way to use an offset
> variable in a zero inflated poisson regression model. I've used the
> following command which seems to test the offset variable as a component of
> the zero inflation part of the outcome variable, but not the count part of
> the outcome:
>
> zip numtxdays cond, inflate(cond, offset(offset)) vce(cluster rctr) vuong
>
> My question is whether or not there's a way to account for the offset
> variable while testing the count part of the model in Stata, and if so, is
> it appropriate to do so? The reason I ask is that, if I use SAS PROC NLMIXED
> or Mplus, I can include the offset variable in the test of the count part of
> the outcome variable, as well. If I do, I get radically different results
> than if it is only accounted for in the inflation part of the model.
I don't know if it is appropriate or not, but you might be able to 
use the constraints option.  Something like

constraint 1 [count]offset=1
zip numtxdays cond offset, inflate(cond, offset(offset)) vce(cluster 
rctr) vuong constraint(1)


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

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/