Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

re: st: Estimation of a Simultaneous Equation Tobit Model with Stata


From   Kit Baum <baum@bc.edu>
To   statalist@hsphsun2.harvard.edu
Subject   re: st: Estimation of a Simultaneous Equation Tobit Model with Stata
Date   Fri, 20 Mar 2009 16:11:07 -0400

<>	
Carlos wrote

I want to estimate a simultaneous equation tobit model with stata;

y1=x1-x5 y2
y2=x1-x5 y1

Have an idea on how to estimate such system? or some sample code?

Per advice commonly given on this list, it is a misconception that this must be done with a systems estimator. Just use -ivtobit- on each equation. But as it stands, the equations of this system are unidentified. If you ignored the censored nature of the y's and tried to estimate this with instrumental variables, you would find there are no available instruments. That needs to be fixed to estimate these equations by any method. That is, either there are plausible exclusion restrictions that cause certain X's not to appear in both equations, or there need to be additional variables available as excluded instruments.

Kit


Kit Baum   |   Boston College Economics and DIW Berlin   |   http://ideas.repec.org/e/pba1.html
An Introduction to Stata Programming   |   http://www.stata-press.com/books/isp.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/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index