Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Stas Kolenikov <skolenik@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: 3SLS with different instruments for different equations |
Date | Mon, 14 Mar 2011 13:10:41 -0500 |
I don't think that's doable within -3sls-. But if you have Stata11, you can use -gmm- to specify different equations and different instruments with them. On Mon, Mar 14, 2011 at 12:21 PM, <etanebay@yahoo.com> wrote: > Hi, I'm having trouble specifying the following model in stata using 3sls. Can you help please? > > Y1 = b0 + b1*Y2 + b2*Y3 + b3*X1 + b4*X2 > > Y2 = k0 + k1*Y1 + k2*IV1 + k3*X1 + k4*X2 > > Y3 = j0 + j1*Y1 + j2*IV2 + j3*X1 + j4*X2 > > Y1 is endogenous to Y2 and Y3. But Y2 and Y3 are not endogenous. > > IV1 is a good instrument for Y2, not Y3, but > IV2 is a good instrument for Y3, not Y2. > > When I type > > reg3 (Y1 Y2 Y3 X1 X2) (Y2 Y1 IV1 X1 X2) (Y3 Y1 IV2 X1 X2), first > > I get in the first-stage results for > Y2 Y1 IV1 X1 X2 __and IV2__ > > Y3 Y1 IV2 X1 X2 __and IV1__ > > As a result, I get strange estimates that differ from the case when I have just Y2 or Y3 (not both) in equation 1 and used 2SLS. > > How do I specify in STATA that my 3SLS equation 2 should not have IV2, and equation 3 should not have IV1? > > Many thanks!! > > May > > > > ------------------ > > * > * 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/ > -- Stas Kolenikov, also found at http://stas.kolenikov.name Small print: I use this email account for mailing lists only. * * 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/