Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: predict after suest


From   "Marc Rosenblum" <Marc.Rosenblum@uno.edu>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: predict after suest
Date   Mon, 1 Dec 2003 10:49:37 -0600

Can anyone offer advice on how to use information from a suest command
to create confidence intervals which take account of the revised SE
estimates?

I have a system of equations:

nbreg Y1 Y2 X1 X2
and
reg Y2 Y1 X3 X4

I am fairly confident that the equations are endogenous to each other,
and so I generate instrumental variables for each endogenous Y, store
the estimates, and then re-run through the suest command (I cannot do
SUREG) since once is a count model and the other a regression model.
Running as suest improves my SE's, as I would expect, but I don't know
how to use take this information and apply to SE's of estimates. I
assume there is a way I can do this by examining the revised
covariance matrix, but not sure of the exact procedure I'd follow. Or
better yet: perhaps someone has written an .ado file that will do the
hard work for me?

Thanks for any advice!

Marc Rosenblum
Assistant Professor of Political Science
University of New Orleans 

*
*   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/



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