Kai,
Date sent: Fri, 17 Oct 2003 09:27:45 +0200
From: Kai Kirchesch <[email protected]>
Organization: HWWA
To: [email protected]
Subject: st: xtabond and instruments
Send reply to: [email protected]
> Hi,
> I am using xtabond, and I want to include an additional instrumental
> variable to replace one specific explanatory variable. The manual only
> refers shortly to the inst option, but this option does not seem to
> create a link between my instrument and the variable I want to
> replace. Is it necessary to specify this link, or does xtabond know
> that this variable is an instrument for one particular variable, so I
> only have to specify this instrument with the inst option, and that's
> it? Thanks, Kai
That's not how single-equation IV works (Arellano-Bond is just a
special case of single-equation IV estimation). There are no
separate links between the various excluded instruments and the
endogenous variables they are instrumenting. In 2SLS language, the y-
hats (fitted values of the endogenous regressors) are obtained by
regressing the y's on *all* the instruments.
Linking the instruments to the various endogenous regressors can be
done, and this is in effect what you do when you estimate a system of
equations - you specify equations for each of your y's in which you
say "this instrument appears and that one doesn't". But when you
estimate in a single-equation framework such as xtabond, the only
structure that's imposed is in the equation you're estimating.
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 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
44-131-451-3008 fax
44-131-451-3485 CERT administrator
http://www.som.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/