Re: [Rd] (PR#9328) Error in optim(...) non-finite finite-difference

From: <ripley_at_stats.ox.ac.uk>
Date: Wed 01 Nov 2006 - 07:56:33 GMT


No, this is not a bug in R, but a report to you by R of a problem with your code. It means that the difference of two values of your function evaluated to a non-finite value when doing finite-differencing. Non-finite values are Inf, -Inf or NaN.

There is nothing to reproduce here, your version of R is long obsolete and you are asking a question. Please do study the FAQ *before* posting an unhelpful non-bug report like this.

On Wed, 1 Nov 2006, avbell@ucdavis.edu wrote:

> Full_Name: Adrian Bell
> Version: 2.2.0
> OS: Windows XP Prof
> Submission from: (NULL) (169.237.62.194)
>
>
> Mysterious error that I do not know how to get around.
>
> Error in optim(...)
> non-finite finite-difference value
>
> For me, this has occurred for methods Nelder-Mead and L-BFGS-B.
>
> What does it mean? Is it a bug? I have tried several things including coercing
> the function being optimized to be finite.
>
> ______________________________________________
> R-devel@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-devel
>

-- 
Brian D. Ripley,                  ripley@stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272866 (PA)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595

______________________________________________
R-devel@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-devel
Received on Wed Nov 01 18:59:22 2006

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.1.8, at Wed 01 Nov 2006 - 09:30:33 GMT.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-devel. Please read the posting guide before posting to the list.