Thanks to Brian for the clarification. Given that, are there
any options in Stata to deal with a tobit with and
endogenous variable that is itself censored?
Thanks for any help
Alejandro
----- Original Message Follows -----
From: "Brian P. Poi" <[email protected]>
To: [email protected]
Subject: Re: st: ivtobit and limited dependent endogenous
variable
Date: Thu, 12 Jul 2007 08:09:58 -0500 (CDT)
> On Wed, 11 Jul 2007, feldman wrote:
>
> > Hi,
> >
> > I know that ivtobit works well with a dummy endogenous
> > variable but I am not sure if
> > Is it ok to use ivtobit when the endogenous variable is
> > a limited dependent variable? More precisely suppose
> > that for 30% of the sample the endogenous variable takes
> > the value 0 and for the rest it has a positive value
> > (the distribution of zeros in the endogenous variable is
> > different to the distribution of zeros in the dependent
> variable). >
>
> Both -ivprobit- and -ivtobit- are for use when the
> endogenous variable is *continuous*. As Wooldridge (2002
> , p. 472) emphasizes, the error terms for the structural
> equation and the equation for the endogenous regressor
> are assumed to be distributed bivariate normal, which
> implies that the endogenous regressor should have
> features of a normal distribution.
>
>
> -- Brian Poi
> [email protected]
>
>
> Wooldridge, J. M. (2002). Econometric Analysis of Cross
> Section and Panel Data. Cambridge, MA: MIT Press.
> *
> * 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/
