# st: estimating the covariance matrix of probit two stage procedure

 From "Armelini, Guillermo" <[email protected]> To <[email protected]> Subject st: estimating the covariance matrix of probit two stage procedure Date Mon, 24 Dec 2007 00:57:04 +0100

```Hello everybody,

I'm trying to estimate a recursive simultaneous equation using a probit model in the selection stage and a conditional censored regression in the second stage. Specifically, the model is the following one:

Z(i)=AV(i)+U(i) (equation 1)

Z(i)=1 if Z(i)>0

Z(i)=0 if Z(i)<=0

where A is a vector of parametes and V is a set of covariates for each (i)

Then I calculate Lambda which is the inverse mills of the predicted values of equation one for those observations in which the Dependent Variable is equal to 1

The second step is to calculate the tobin model:

Y(i)=bX(i)+E(i) if Z(i)=1  (second equation)

In this equation "bs" are the coefficients to be estimated and "X" is a vector of covariate which includes Lambda (which is the inverse mills of the predicted values of equation one in which the DV is = 1)

My question is how can I correct the covariance and the variance of the parameters since, Lee, Maddala  and Trost (1980) suggest that everytime a two stage model like the one I describe before is estimated, a procedure to correct the variance and covariance of the parameters should be run.

Is anybody aware about how to do this in Stata?

Guillermo

This message has been scanned for viruses by TRENDMICRO,
an IESE technology affiliate company  and global leader in antivirus and content security software.

*
*   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/
```