[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
RE: ivhettest: heteroskedastic IV in panel estimation
> -----Original Message-----
> From: firstname.lastname@example.org
> [mailto:email@example.com] On Behalf Of
> Vincenzo Lombardo
> Sent: Sunday, July 23, 2006 10:22 AM
> To: firstname.lastname@example.org
> Subject: ivhettest: heteroskedastic IV in panel estimation
> dear all,
> i am using this commands (ivreg2, gmm) for my panel
> estimation; my issue is this one: i have to assess if using
> IV estimation, that is I have basically to perform a test of
> endogeneity. Now, in my panel there is presence of
> heteroskedasticity and serial correlation (within cluster and
> over time); then I tried two basic way to deal with this:
> 1) estimating the classical iv panel model re (xtivreg, re),
> estimating the model not instrumented (xtreg, re) and then
> performing the hausman-type test on the two models; results
> not need to instrument!!!
But if there is heteroskedasticity and autocorrelation, then xtreg,re is
not efficient, so the Hausman test is invalid. Or am I missing
> 2)then, taking into account the fact the the above
> estimations do not consider the presence of
> heteroskedasticity and correlation (xtivreg and xtreg are not
> allowed for this), i am using ivreg2, gmm (because it has
> been showed that in this cases GMM is more efficient than IV)
> with robust-cluster option.
Shouldn't you use xtivreg2 instead of ivreg2? The former is a wrapper
for the latter but gets things like degrees-of-freedom adjustments
right. Or you can use ivreg2 but with explicit fixed effects dummies.
> 3) QUESTION: can I use after step 2, above, the command
> ivhettest to demostrate the presence of heteroskedasticity in
> the second model, even if my dataset is panel?
Actually, this is a reason to use ivreg2 with explicit dummies.
ivhettest won't work after xtivreg2, but will work after ivreg2 with
Prof. Mark E. Schaffer
Centre for Economic Reform and Transformation
Department of Economics
School of Management & Languages
Edinburgh EH14 4AS UK
> finally, do you think that the step 1 can give consistent
> result of the endogeneity test, that i did?
> thanks a lot for your attenction,
> warm regards, vincenzo.
> Vincenzo Lombardo
> University of Sussex, Dept. of Economics University of Napoli
> Parthenope, DSE
> 12 Canfield Road
> BN2 4DN Brighton - UK
> tel. (UK):++44(0)7765991711
> tel. (ITALY):++393284164302
> * 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: