Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

st: RE: IV probit and non convergence


From   Nick Cox <n.j.cox@durham.ac.uk>
To   "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu>
Subject   st: RE: IV probit and non convergence
Date   Tue, 12 Oct 2010 17:27:27 +0100

You need to look more at your data. Are there high correlations between? Are there inbuilt relations among some of your predictors (e.g. constraints that they sum to a constant)? What happens with pairs of predictors?

Nick 
n.j.cox@durham.ac.uk 

Mariana Spatareanu Manole

I am running ivprobit regressions, and I have 4 endogenous continuous
variables -  I can run the regressions with only one endogenous
variable at a time,

but the ivprobit does not converge when I introduce all of them in
the regression.

It keeps on running and displays the following:

Fitting full model

Iteration 0:   log pseudolikelihood = -19244.386
Iteration 1:   log pseudolikelihood = -19243.321  (not concave)
...
Iteration 35:  log pseudolikelihood = -19242.958  (not concave)
Iteration 36:  log pseudolikelihood = -19242.958  (not concave)

Do you have any suggestions what to do in  cases like this?

*
*   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 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index