On 08-Feb-10 14:50:59, Paul Hiemstra wrote: > Juliane Struve wrote: >> Dear list, >> >> I am looking for an R-only implementation of a Nelder-Mead process >> that can find local maxima of a spatially distributed variable, e.g. >> height, on a spatial grid, and outputs the coordinates of the new >> point during each evaluation. I have found two previous threads about >> this topic, and was wondering if something similar has been implemented >> since those messages were posted. >> >> Thank you for any suggestions how to approach this task or where to >> look. >> >> Juliane >> >> Previous posts: >> >> www.mail-archive.com/r-help@r-project.org/msg13078.html >> http://www.nabble.com/Nelder-Mead-with-output-of-simplex-vertices-tp258 >> 38572p25869383.html >> >> Dr. Juliane Struve >> Environmental Scientist >> 10, Lynwood Crescent >> Sunningdale SL5 0BL >> 01344 620811 >> > Hi, > > Look at the optim() function, it has Nelder-Mead implemented. > > cheers, > Paul > > -- > Drs. Paul Hiemstra
The problem with the optim() function (and the reason I made the query which started the second thread cited by Juliane) is that optim() does not have an option for outputting the details of each successive simplex. So, while it implements Nelder-Mead, it will jnot meet Juliane's needs (as it did not meet mine). I have written privately to Juliane with R code which is a modification (bug-fix) of code which Ben Bolker sent to me privately in response to my query (see also in that thread). Ben had identified a potential copyright problem if the code were publicly distributed: "The reason I haven't shared is that the code is a translation from _Numerical Recipes in C_. Therefore I'm uncertain about its redistribution status. If it were a straight transcription rather than a translation, it would be un-redistributable (I feel bound to honor Press et al's redistribution policy, even though it's really annoying: see http://mingus.as.arizona.edu/~bjw/software/boycottnr.html ). Because it's a translation of their C implementation of a public-domain algorithm, it's less clear to me whether this is allowed or not (any intellectual property lawyers lurking on the list should feel free to chime in here!); my compromise is that I'm willing to send the code on request, but won't post it to the list." (See http://finzi.psych.upenn.edu/Rhelp10/2009-October/214829.html ) It seems that no lurking IP Lawyers have since chimed in! Therefore I am adopting the same policy as Ben did. Once again, are there any intellectual proprty lawyers out there? Ted. -------------------------------------------------------------------- E-Mail: (Ted Harding) <ted.hard...@manchester.ac.uk> Fax-to-email: +44 (0)870 094 0861 Date: 08-Feb-10 Time: 15:28:20 ------------------------------ XFMail ------------------------------ ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
