Re: st: binary endogenous variable

 From Mark Schaffer <[email protected]> To [email protected], "S.Rahardja" <[email protected]> Subject Re: st: binary endogenous variable Date Sun, 25 Jul 2004 13:00:38 +0100 (BST)

```Sjamsu,

Quoting "S.Rahardja" <[email protected]>:

> Mark,
> Thank you for the tips.
> At first I'd thought about running an IV, but then I
> started thinking about the consequences on fitting a
> binary variable using linear model i.e. the predicted
> value from the 1st stage from a binary variable won't
> be bounded between 0 and 1.

It doesn't matter; the coefficient estimate will still be consistent if you
use IV.  See, e.g., Heckman and Robb (1985) (in Heckman and
Singer, "Longitudinal Analysis of Labor Market Data", CUP), p. 185, who
point out that the advantage of IV is that it "is the least demanding in
the a priori conditions that must be satisfied for its use."

The only thing you need to be aware of is Wooldridge's recommendation that
a heteroskedastic-robust F-statistic is used when interpreting the first-
stage regression statistics.  See Wooldridge's (2002) book, p. 92.

Cheers,
Mark

>
> I'll look at the treatment effect approach.
>
> Regards.
>
> Sjamsu
>
> --- Mark Schaffer <[email protected]> wrote:
> > There are at least two approaches you can follow.
> >
> > First, you can estimate the system using -treatreg-.
> >  That means you also
> > specificy a probit-type treatment equation for your
> > endogenous dummy.  -
> > treatreg- estimates the treatment equation and the
> > outcome equation for y
> > as a system.
> >
> > Second, if want to estimate only the outcome
> > equation y, you can simply
> > use -ivreg- or -ivreg2-.  Consistency of IV does not
> > require the endogenous
> > variable(s) to be continuous; endogenous dummies are
> > fine.  The results
> > won't be as efficient as with the sytem estimation
> > using -treatreg-, but
> > they will have the advantage (as usual with
> > single-equation methods) of
> > being consistent under a broader range of
> > assumptions than the system
> > estimation results.
> >
> > Hope this helps.
> >
> > --Mark
> >
> > Quoting "S.Rahardja" <[email protected]>:
> >
> > > Dear Colleagues,
> > >
> > > I wonder if you could give me tips on how should I
> > > deal with an endogenous dummy variable.
> > > What I'm thinking is to run using OLS, say:
> > > y = a + bX + dD + e
> > >
> > > where D= 0|1 is the endogenous dummy variable.
> > >
> > > Or, does this sound more like a selection problem
> > > (where I can split the sample into two) ?
> > >
> > > Thank's in advance.
> > >
> > >
> > >
> > >
> > > __________________________________
> > > Do you Yahoo!?
> > now.
> > > http://messenger.yahoo.com
> > > *
> > > *   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: [email protected]
> > 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
> > e-mail.  Heriot
> > 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,
> > 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/
> >
>
>
>
>
> __________________________________
> Do you Yahoo!?
> Yahoo! Mail Address AutoComplete - You start. We finish.
> http://promotions.yahoo.com/new_mail
> *
> *   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: [email protected]
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/
```