Liesbet,
Subject: st: 2SLS - two censored variables
Date sent: Fri, 2 Jul 2004 12:02:24 +0200
From: "Vranken, Liesbet" <[email protected]>
To: <[email protected]>
Send reply to: [email protected]
> Dear stata-listers,
>
>
>
> Could someone give me some guidance on the following estimation
> issue?�
>
> I would like to use 2SLS in order to control for endogeneity. The
> dependent variable of the second stage is censored at zero. Also the
> endogenous variable that I am instrumenting for is censored at zero.
> So the first and second stage would be a tobit as both variables are
> censored at zero.� Is possible to do such IV? If so, how does one do
> such IV?
You probably want to use Joe Harkness' ivtobit, which implements
Amemiya's GLS estimator for tobit with endogenous regressors. Just
findit ivtobit
from within Stata and follow the links to install.
It's worth noting that if you are estimating just the "second-stage"
equation, it shouldn't matter for consistency of the estimates
whether or not the endogeneous variable that you are instrumenting is
censored. (Caveat: this is true for standard IV and I am 99% sure it
is true for Amemiya's IV tobit estimator, but I confess I haven't
checked the article to confirm it.)
Hope this helps.
--Mark
>
> Thanks a lot in advance!
>
> Liesbet
>
>
> *
> * 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/
