# Re: st: Treatreg with two regression equations?

 From Mark Schaffer To statalist@hsphsun2.harvard.edu, Jennifer Alix Subject Re: st: Treatreg with two regression equations? Date Thu, 27 Mar 2003 18:03:39 +0000 (GMT)

```Jennifer,

Quoting Jennifer Alix <alix@are.berkeley.edu>:

> Thanks for your speedy response Mark.  I've tried the switchr, and
> it has
> been useful in confirming that I need different variables in my two
>
> component regressions.  I cringe at the idea of programming this
> myself,
> but it looks like I'm going to have to commit to those inevitable
> hours of
> frustration in front of my computer.
>
> Jennifer

Two quick thoughts that might save you a little time.

First, if you're at the exploratory stage, depending on the specification
it might be enough for your purposes to use the full set of regressors in
both of the two regime equations.  Say that regime one has regressor x1 and
regime two has regressor x2.  Under the null, x2 doesn't belong in regime
one and hence should be insignificant, and visa-versa with regime two and
x1.  Including x1 and x2 in both regime one and regime two may still yield
consistent estimates of the coefficients that you care about (x1 in regime
one and x2 in regime two).

Second, and a bit obvious but worth pointing out anyway - you might find it
easier to modify Fred Zimmerman's -switchr- code than to program your own
version from scratch.

Cheers,
Mark

>
> At 04:37 PM 3/27/2003 +0000, you wrote:
> >Jennifer,
> >
> >Quoting Jennifer Alix <alix@are.berkeley.edu>:
> >
> > > Hello,
> > >
> > > Does anyone know if there is a way to specify two different
> > > regression
> > > equations for the treatreg command?  That is to say, I have a
> > > problem where
> > > regime choice is known, but once the selection is made, the
> two
> > > different
> > > groups have entirely different behaviors.  Treatreg (and
> heckman)
> > > seem only
> > > to offer the option of one second-stage regression equation.
> > >
> > > Thanks,
> > > Jennifer
> >
> >The closest thing to what you want that is available (and that I'm
> aware
> >of) is Fred Zimmerman's -switchr-, which estimates a switching
> regression.
> >The 2 "second-stage" regressions (a bit of a misnomer because
> everything is
> >simultaneous) have to have the same regressors but the coefficients
> can be
> >completely different.
> >
> >-findit switchr- for more details.
> >
> >Hope this helps.
> >
> >--Mark
> >
> > >
> > >
> > > *
> > > *   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/
> > >
> >
> >
> >
> >Prof. Mark Schaffer
> >Director, CERT
> >Department of Economics
> >School of Management & Languages
> >Heriot-Watt University, Edinburgh EH14 4AS
> >tel +44-131-451-3494 / fax +44-131-451-3008
> >email: m.e.schaffer@hw.ac.uk
> >web: http://www.sml.hw.ac.uk/ecomes
> >________________________________________________________________
> >
> >DISCLAIMER:
> >
> >This e-mail and any files transmitted with it are confidential
> >and intended solely for the use of the individual or entity to
> >whom it is addressed.  If you are not the intended recipient
> >you are prohibited from using any of the information contained
> >in this e-mail.  In such a case, please destroy all copies in
> >Watt University does not accept liability or responsibility
> >for changes made to this e-mail after it was sent, or for
> >viruses transmitted through this e-mail.  Opinions, comments,
> >conclusions and other information in this e-mail that do not
> >relate to the official business of Heriot Watt University are
> >not endorsed by it.
> >________________________________________________________________
> >*
> >*   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/
>
>
>
> *
> *   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/
>

Prof. Mark Schaffer
Director, CERT
Department of Economics
School of Management & Languages
Heriot-Watt University, Edinburgh EH14 4AS
tel +44-131-451-3494 / fax +44-131-451-3008
email: m.e.schaffer@hw.ac.uk
web: http://www.sml.hw.ac.uk/ecomes
________________________________________________________________

DISCLAIMER:

This e-mail and any files transmitted with it are confidential
and intended solely for the use of the individual or entity to
whom it is addressed.  If you are not the intended recipient
you are prohibited from using any of the information contained
in this e-mail.  In such a case, please destroy all copies in
Watt University does not accept liability or responsibility
for changes made to this e-mail after it was sent, or for
viruses transmitted through this e-mail.  Opinions, comments,
conclusions and other information in this e-mail that do not
relate to the official business of Heriot Watt University are
not endorsed by it.
________________________________________________________________
*
*   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/
```