Dear friends - updated to R 3.3.2 - tried to install nls - got this sad response package ?nls? is not available (as a binary package for R version 3.3.2) I'm on windows 7 Did I do something wrong? Will a binary appear eventually? Would I have to make it myself? Best wishes Troels Ring Aalborg, Denmark
> On 29 Nov 2016, at 09:30, Troels Ring <tring at gvdnet.dk> wrote: > > Dear friends - updated to R 3.3.2 - tried to install nls - got this sad response > > package ?nls? is not available (as a binary package for R version 3.3.2) > > I'm on windows 7 > > Did I do something wrong? Will a binary appear eventually? Would I have to make it myself? >Indeed you did something wrong. nls is part of the stats package in R. Just do ?nls to see the help. Berend Hasselman> Best wishes > > Troels Ring > > Aalborg, Denmark > > ______________________________________________ > R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see > 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.
> On Nov 29, 2016, at 12:30 AM, Troels Ring <tring at gvdnet.dk> wrote: > > Dear friends - updated to R 3.3.2 - tried to install nls - got this sad response > > package ?nls? is not available (as a binary package for R version 3.3.2) > > I'm on windows 7I don't see an `nls` package on CRAN. Perhaps it has been replaced by nls2. On the other hand, you may be looking for the functions `nls` in the stats package. (Hard to tell from the available information.) packageDescription('nls2') Package: nls2 Version: 0.2 Date: 2013-03-07 Title: Non-linear regression with brute force Author: G. Grothendieck Maintainer: G. Grothendieck <ggrothendieck at gmail.com> Description: Adds brute force and multiple starting values to nls. Depends: proto Suggests: nlstools License: GPL-2 BugReports: http://groups.google.com/group/sqldf URL: http://nls2.googlecode.com> > Did I do something wrong? Will a binary appear eventually? Would I have to make it myself? > > Best wishes > > Troels Ring > > Aalborg, Denmark > > ______________________________________________ > R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see > 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.David Winsemius Alameda, CA, USA
You may also want to use tools that are more robust. Package nlmrt uses analytic Jacobian where possible and a Marquardt solver. Package minpack.lm uses a Marquardt solver, but the forward difference derivatives of nls() for its Jacobian. alpha level work in https://r-forge.r-project.org/R/?group_id=395 package nlsr is aimed at cleaning up some of the work in nlmrt and extending its capabilities. JN On 16-11-29 03:30 AM, Troels Ring wrote:> Dear friends - updated to R 3.3.2 - tried to install nls - got this sad response > > package ?nls? is not available (as a binary package for R version 3.3.2) > > I'm on windows 7 > > Did I do something wrong? Will a binary appear eventually? Would I have to make it myself? > > Best wishes > > Troels Ring > > Aalborg, Denmark > > ______________________________________________ > R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see > 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.