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

st: RE: Pgmhaz - Convergence

From   "Stephen P Jenkins" <>
To   <>
Subject   st: RE: Pgmhaz - Convergence
Date   Fri, 27 Feb 2004 14:24:51 -0000

> -----Original Message-----
> From: 
> [] On Behalf Of 
> Vartia, Niini
> Sent: 27 February 2004 13:51
> To:
> Subject: st: Pgmhaz - Convergence
> Hi!
> I am using the Jenkins pgmhaz procedure to estimate a 
> discrete time non-parametric proportional hazard model. I 
> would like to ask about the estimation of the second model. 
> During the iteration process I have received different 
> messages: unproductive step attempted and nonconcave function 
> encountered, but in the end the convergence has been 
> achieved. However, when I run a slightly different 
> specification I now receive the following error message: 
> pgm_ll does not compute a continuos nonconstant function/ 
> could not calculate numerical derivatives. Does this imply 
> that there was no convergence? What is the best way to 
> proceed in such case? 

Please check the Statalist archives before posting questions like this.
A very similar question was answered before -- please see below

> -----Original Message-----
> From: 
> [] On Behalf Of Jenkins S P
> Sent: 10 October 2003 23:15
> To:
> Subject: Re: st: pgmhaz convergence (hazard functions)
> On Fri, 10 Oct 2003, Monica L. Parra Torrado wrote:
> > Dear Stata List,
> >  I am running the Jenkins porcedure pgmhaz with non parametric 
> > estimation of the baseline hazard, i.e., I am including 
> weekly dummies 
> > instead of "log(seqvar)" However, it has run for 120 hours and 35 
> > iterations and has not come up with any result yet.  After the last 
> > ten iterations it has been displaying the message 
> "unproductive step 
> > attempted".  Does this mean it will not converge? I have run this 
> > model with diferent specifications and although this 
> message appeared 
> > sometimes, it did converge. How can I know that the 
> maximization will 
> > not converge? Does Stata give up at any moment?  Shall I wait till 
> > then? Or does stata keep trying forever? What should I do?
> Be patient, perhaps.
> The program often runs (very) slowly, given use of numerical 
> derivatives, and the relatively large size of social science 
> data sets.  Moreover the likelihood surface is not globally 
> concave, so convergence problems can be common, especially 
> when one specifies a non-parametric baseline hazard. (Ensure 
> too that you have events at each and every interval.) It is 
> often a good idea to run -pgmhaz- with the -trace- option on 
> so that you can see if there are any problematic parameters. 
> (E.g. the program trying to force the gamma variance towards 
> zero, i.e. log variance towards a large negative number?)  
> ... hence maybe experiment with different starting values for 
> the (log) gamma variance.  All this is mentioned in the 
> original STB article, a version of which is available (in MS 
> Word)  from my Survival Analysis Using Stata webpages.
> good luck Stephen
> PS -pgmhaz- stands for Prentice-Gloeckler-Meyer HAZard 
> regression, after the original proposers of the model -- 
> there is no J in it. (PG for the grouped data proportional 
> hazards model;  M for adding in gamma distributed unobserved 
> heterogeneity.)

Professor Stephen P. Jenkins <>
Institute for Social and Economic Research
University of Essex, Colchester CO4 3SQ, U.K.
Tel: +44 1206 873374.  Fax: +44 1206 873151.   

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index