On Tue, 8 Aug 2000 chrisl at agsm.edu.au wrote:
>
> I have had problems with the function optimize/optimise
> for maximising/minimising a function of one variable. It
> seems to get easily fooled by local optima. Obviously
> this can happen to any numerical optimiser but some of
> the examples I have a pretty disappointing. Any comments
> of suggestions of a better R-function?
Under at least some circumstances optim() will work better for 1D problems.
I think it is usually assumed that in 1D problems one can find a
reasonable starting interval by, e.g. a grid search.
It is of course possible that there is a bug in optimize (one lurked
in S-PLUS's optimize for many years) so you might like to send some
examples to R-devel.
--
Brian D. Ripley, ripley at 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 272860 (secr)
Oxford OX1 3TG, UK Fax: +44 1865 272595
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !) To: r-help-request at
stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._