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

st: bivariate probit


From   "Axel Heitmueller" <A.Heitmueller@hw.ac.uk>
To   statalist@hsphsun2.harvard.edu
Subject   st: bivariate probit
Date   Thu, 27 Mar 2003 19:39:24 -0000

hi there,

I'm running biprobits and need to calculate out-of-sample 
predictions afterwards which can be done by using one of the 
predict commands. yet, I also need to calculate a new rho for 
these predictions. the initial idea was to use the linear predictions, 
calculate the new error terms by simply do y-xbhat and then get 
the correlation between them. however, I've tried to do that for 
e(sample) predictions in order to replicate the rho given by stata 
and the manual rho is by no means identical. is this a 
consequence of stata's way to estimate rho in the maximum 
likelihood and is there any way to replicate rho manually for out of 
sample predictions?

cheers

axel

Axel Heitmueller, 
Centre for Economic Reform and Transformation, CERT
School of Management
Heriot-Watt University
Edinburgh
EH14 4AS
UK
phone +44(0)131 451 3969
fax +44 (0)131 451 3296
a.heitmueller@hw.ac.uk
www.som.hw.ac.uk/somah3/
*
*   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