Vincenzo,
> -----Original Message-----
> From: [email protected]
> [mailto:[email protected]] On Behalf Of
> Vincenzo Lombardo
> Sent: Thursday, July 20, 2006 12:59 PM
> To: [email protected]
> Subject: st: IV in Panel
>
> dear all,
> i am trying to figure out if I have to use instrumental
> variables in a panel regression; now, how to look at if the
> instruments are good?that is, they must be correlated with
> the regressor (endogenous candidate) and orthogonal to the
> errors
xtivreg2 supports the diagnostic statistics for this for linear fixed
effects estimation.
>...then, orthogonal to which errors in the panel? the
> fixed error component, the random one, or the overall?
Depends on whether you are using a fixed or random effects estimator.
The orthogonality conditions for the fixed effects estimator refer only
to the idiosyncratic error; the orthogonality conditions for the random
effects estimator refer to this plus the group error component (which is
why it is more efficient but less robust than the fixed effects
estimator).
Cheers,
Mark
Prof. Mark E. Schaffer
Director
Centre for Economic Reform and Transformation
Department of Economics
School of Management & Languages
Heriot-Watt University
Edinburgh EH14 4AS UK
44-131-451-3494 direct
44-131-451-3296 fax
http://www.sml.hw.ac.uk/cert
> *
> * 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/
