Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: reg3 and restricting some IVs for reduced-form regressions


From   Austin Nichols <austinnichols@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: reg3 and restricting some IVs for reduced-form regressions
Date   Thu, 10 Dec 2009 14:59:24 -0500

Ekrem Kalkan <kalkan.ekrem@gmail.com> :
Read the manual entry on -gmm- in Stata 11 for a multi-equation IV
with different instruments by equation.

On Thu, Dec 10, 2009 at 2:43 PM, Ekrem Kalkan <kalkan.ekrem@gmail.com> wrote:
> Hello Dear Stata users,
>
> In a presentation prepared by C. Baum (see the site
> http://fmwww.bc.edu/ec-c/s2009/771/DIWMar2008.beamer.pdf, page 38),
>
> it is said that it is possible to restrict certain instruments to
> enter certain first-stage regressions by specifying  a full
> simultaneous system of equations and by using the command "reg3". As
> far as I know in "reg3", all instruments specified in option exog( )
> are used in reduced form regressions. Does anybody know how to do
> Baum's suggestion ?
> More concretely, I am currently estimating a demand system using AIDS
> model. Prices (P1, P2 etc.) are assumed to be endogenous. I assume
> instrument IV1 is correlated with P1, but I do not want to use IV1 for
> P2, for example.
>
> Thank you.
>
> Ekrem Kalkan

*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index