Dear Maarten,
you arr right, I could use a dummy for the problem I described earlier. Unfortunately, in order to formulate my problem as simple as possible I described it wrong. Sorry. Actually I want to do the following:
ivregress y (a = x y z) b c
est store one
ivregress y (a = x y z) b c d
est store two
suest one two
test varaone = varatwo
godiva
-----Ursprüngliche Nachricht-----
Von: "Maarten buis" <[email protected]>
Gesendet: 24.07.09 00:34:12
An: [email protected]
Betreff: Re: st: Wald test across equations after ivregress or ivreg2
This kind of test much much easier when you estimate one model for both groups, and allow the parameters to differ across groups using interaction terms.
Hope this helps,
Maarten
-----------------------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
--- On Thu, 23/7/09, [email protected] <[email protected]> wrote:
> From: [email protected] <[email protected]>
> Subject: st: Wald test across equations after ivregress or ivreg2
> To: [email protected]
> Date: Thursday, 23 July, 2009, 9:43 PM
>
> I have trouble figuring out how to do a wald test after iv
> regressions
> I have 2 iv regressions of the same type with the same
> instruments for different subgroups
>
> I would like to test if the coefficients of the
> instrumented variable in the two estimations differ
> significantly (F-, or Wald-Test).
>
>
> I figured out how to do it in OLS:
>
> reg y a b c if group == 1
> est store one
> reg y a b c if group == 2
> est store two
> suest one two
>
> test var1one = var1two
>
> I would like to do the same after estimating two IV
> regressions (ivreg2 or ivregress).
>
> There was earlier a related question with following answer
> but ivreg2 has not longer the option pscore:
>
> >>There is a bug in suest. Official Stata's ivreg
> (and our ivreg2) store a score variable, on request, as
> e(pscorevar). suest will not look there for it, demanding
> that it be named in e(scorevar). So the trick is...
>
> ivreg2 ..., pscore(one)
> est store one
> est change one, scorevars(one)
> ivreg2 ..., pscore(two)
> est store two
> est change two, scorevars(two)
> suest one two
> <<
>
> Does someone know how to store the estimation results such
> that STATA can compare the coefficients over the two iv
> equations?
>
> Any help would be great
>
> godiva
> ______________________________________________________
> GRATIS für alle WEB.DE-Nutzer: Die maxdome Movie-FLAT!
> Jetzt freischalten unter http://movieflat.web.de
>
>
> *
> * 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/
______________________________________________________
GRATIS für alle WEB.DE-Nutzer: Die maxdome Movie-FLAT!
Jetzt freischalten unter http://movieflat.web.de
*
* 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/
