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: Newton-Raphson (not concave)


From   "Nick Cox" <[email protected]>
To   <[email protected]>
Subject   st: RE: Newton-Raphson (not concave)
Date   Wed, 14 Apr 2010 11:49:31 +0100

I'd say that while failure to converge is almost always diagnostic of a poor model (or poor data), small struggles in convergence are rarely diagnostic of anything much, especially with complicated models like these. 

But wondering whether a simpler model is preferable is always good science and good statistics. 

Nick 
[email protected] 

Dimitrije Tišma

I am running a multi-level random intercept model and after the
adaptive quadrature has converged I have got four consecutive
iterations with (not concave) message. If the model does converge
should I believe my results or should I try another simpler model by
taking out one or two variables? 

*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index