Hello
I am using the Hausman Taylor estimator for my analysis and wonder if:
a) it is adjusted to accommodate an unbalanced sample
b) corrects for the bias of heteroskedasticity specific to the unbalanced
sample.
If no to any of the above, would someone on this list have a code for a do
file to deal with it?
many thanks
seema
----- Original Message -----
From: "Kit Baum" <[email protected]>
To: <[email protected]>
Sent: Wednesday, November 28, 2007 2:09 PM
Subject: st: re: 2SLS and Hausman test
> An equivalent test can be performed by -ivreg2-. But in the example you
> give below the equation is not identified. You must have at least one
> exogenous regressor in the parenthesized list that is not already in the
> equation.
>
> ivreg2 ad pse bonus leverage pricebook beta lnsize blockown (roa = pse
> bonus leverage pricebook beta lnsize )
>
> What you have written is equivalent to
>
> ivreg ad pse bonus leverage roa pricebook beta lnsize blockown (roa = )
>
> as all of your instruments are already included exogenous regressors.
>
> Let's say you had two additional instruments available, Z1 and Z2. Then
> you could say
>
> ivreg2 ad pse bonus leverage roa pricebook beta lnsize blockown (roa = Z1
> Z2), endog(roa)
>
> and the -endog()- option would do the test of endogeneity, equivalent
> to -hausman-.
>
> Please see help for -ivreg2- (findit ivreg2).
>
> Kit
>
> Kit Baum, Boston College Economics and DIW Berlin
> http://ideas.repec.org/e/pba1.html
> An Introduction to Modern Econometrics Using Stata:
> http://www.stata-press.com/books/imeus.html
>
>
> *
> * 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/
