Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: RE: -ivprobit- warning: equation(s) Y not found


From   "Brian P. Poi" <bpoi@stata.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: RE: -ivprobit- warning: equation(s) Y not found
Date   Wed, 17 Dec 2008 10:40:34 -0600 (CST)

On Wednesday, December 17, 2008 12:38 AM, Nirina wrote:

Hello,
I run ivprobit, twostep and I got this message after  -mfx - and I
don't undersntand what it means:

warning: equation(s) Y not found

warning: equation list empty. Default full variable list used.


Y is my binary dependent variable.


You can safely ignore this warning message. -mfx- after -ivprobit- expects the coefficient matrix to have equation names attached to it, though the two-step estimator does not attach them. We will fix things so that this warning is not produced in this application.

Note, however, that after the two-step estimator, predicted probabilities cannot be computed. All you can get from -mfx- after -ivprobit, twostep- are the marginal effects of the linear index equation -- which are the coefficients reported by -ivtobit, twostep-!

   -- Brian Poi
   -- bpoi@stata.com

*
*   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/



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