st: re: Discrete endogenous variables in 2SLS?

[Christopher Baum <baum@bc.edu>]

<>
Jeffrey said
Can XTIVREG be used in the case of discrete endogenous variables in  
some way? I have a problem such as: Y = f(a,b,c) a = f(z,b,c) where  
'a' is a dichotomy. For 'z' to be an instrument for 'a' then there is  
a co-linearity problem.
If the command
xtivreg y (a=z) b c, fe
has a collinearity problem, it indicates that there is something wrong  
with the set (z b c iota) as instruments. That sounds to me like a  
case of 'perfect prediction'. What happens if you try to estimate the  
dichotomous equation
probit a z b c
does that complain of 'perfect prediction'? If that is the case then  
your main equation is not identified.
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/