Re: st: xtnbreg and mfx

["Donghyun Lee" <dlee12@uoregon.edu>]

Thank you Maarten.
So then I should specify predict(nu0) after mfx (since I want marginal effect for predicted number of events)? 
But nu0 assumes zero fixed effects right? Does this mean stata will calculate marginal effect for the regression without fixed effects?
Just wanted to make sure if I can interpret the coefficients from mfx, predict(nu0) as marginal effects for my fixed effects negative binomial regression.

Thanks again for your help.

Don


On Tue, 17 Aug 2010 07:33:40 +0000 (GMT), Maarten buis <maartenbuis@yahoo.co.uk> wrote:
> --- On Tue, 17/8/10, Donghyun Lee wrote:
> > I'm using xtnbreg for my work and I'm trying to get the
> > marginal effect. However, when I type mfx after running
> > the regression using xtnbreg, the coefficients are the
> > same as before
> 
> If you don't specify the -predict()- option in -mfx-, then
> -mfx- will use the default predict option of the preceding
> estimation command. The default predict option for -xtnbreg-
> is the linear predictor, so that is why you got the same
> coeficients. The solution is to specify the -predict()- 
> option or interpret the incidence ratios, which follow more
> naturaly from count models.
> 
> Hope this helps,
> Maarten
> 
> --------------------------
> Maarten L. Buis
> Institut fuer Soziologie
> Universitaet Tuebingen
> Wilhelmstrasse 36
> 72074 Tuebingen
> Germany
> 
> http://www.maartenbuis.nl
> --------------------------
> 
> 
>       
> 
> *
> *   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/

*
*   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/