Re: [R] nls() and "singular grandient"

Tue, 22 Mar 2005 07:07:11 -0800

Many people could help you, but the question is too general. In brief, it means that the algorithm has found a place where the (estimated?) matrix of first or second partial derivatives is of reduced rank, and it refuses to do more. For such problems, I often use "optim".

If you need more specifics, PLEASE do read the posting guide! "http://www.R-project.org/posting-guide.html";, prepare a very simple example of what you get, and submit that to this list. Many people find answers to their questions in the process of preparing a post following this guide, and those that don't, I believe, are more likely to get more informative replies. 

     spencer graves

Guillaume STORCHI wrote:

Hello,

I have a problem with nls() when I want to fit a model with more than two
parameters to be fitted which are written as start=list(a1=,a2=,a3=,...).
Everytime, it displays:'error... singular gradient'
it's a real pain!!! 

Hope sb knows something about this

Thanks

GS

______________________________________________
[email protected] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html



______________________________________________
[email protected] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html

Reply via email to