Re: st: Instrumental Variables

[jean ries <ries@ires.ucl.ac.be>]

Rodriguez, Maria Victoria wrote:

> I have a doubt and I will appreciate anybody`s help.
>
> I need to use instrumental variables in a logit model. Is this posible?
> Is de two.stage least squares method applicable to logit models?
>  
Here are some possibilities that might interest you:

1. Estimate a linear probability model by two stage least squares
2. If your endogenous variable is continuous you could use -ivprob-. 
N.B. this is not an official command: -findit ivprob- will take you to it
3. If your endogenous variable is binary, you could use -biprobit-

Wooldridge (2002) is discussing this in chapter 15.7.2 and 15.7.3

Jeffrey M. Wooldridge, (2002), Econometric Analysis of Cross Section and 
Panel Data, MIT Press.

Hope this helps,

jean
*
*   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/