I never heard of an IV multinomial logit for Stata (see also the thread appeared in January 2007: Oprobit in first stage of two-step model) --- but it may exist.
The nearest thing in my user-written command library is -mtreatnb- from SJ6-4, that fits a treatment-effects model that considers the effects of an endogenously chosen multinomial treatment on another endogenous count outcome, conditional on two sets of independent variables. The treatment variable is modeled via a multinomial logistic and the outcome via a negative binomial regression.
Sorry: not sure it helps,
Nicola
At 02.33 08/03/2007 -0500, you wrote:
>Dear all,
>I'm a Phd Student in Economics of the university of Turin (Italy). I've the=
> following problem. I want to estimate the following panel data model:
>
>- - music_sales(it) =3D a(0) + a(1) price(it) + a(2) piracy(it) + A(k) other =
>explanatory variable
>
>- - piracy(it) =3D b(0) + b(1) price(it) + a(k) explanathory variable + a(n)=
> additional instrument
>
>However, piracy is a categorical variable..
>Have someone a suggestion to how I can estimate such a model, both from a t=
>heoretical and an applied point of view (using stata 9)?
*
* 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/
