[Top][All Lists]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Help-gsl] Nonlinear fitting

From: jeremy theler
Subject: Re: [Help-gsl] Nonlinear fitting
Date: Thu, 03 Jul 2014 20:59:55 -0300
User-agent: KMail/4.12.4 (Linux/3.2.0-4-amd64; KDE/4.13.1; x86_64; ; )


If you just need a quick answer to your problem, I would like you to try my 
tool called wasora, which amongst other things, is a high-level interface to 
some of the GSL tools.

I have added your fitting problem to the examples subdirectory (I made up the 
data). You can take a look at it by first downloading the tarball from

and the looking at examples/fit.was

Sadly, the code is lacking good documentation. So far all I have are examples 
of usage. In the following link

some comparison between GSL examples written in C as taken from the manual and 
the (almost) the same results obtained with wasora by using a far more simple 
high-level input file.

Regarding your fitting problem, wasora takes care of numerically computing the 
gradient of the function with respect to the parameters if explicit algebraic 
expressions are not given.


On Thursday 03 July 2014 18:07:40 address@hidden wrote:
> Hi,
> I am trying to fit the nonlinear equation:
> P = C0 + C1*X + C2*X^r
> where C0, C1, C2 and r are variables to be fitted, P and X are vectors
> of known observations.
> I have read the docs and I'm trying to modify the example program. I'm
> struggling to provide the expb_f, expb_df, expb_fdf functions.
> I would like advice on how to proceed.
> Regards,
> Ken

reply via email to

[Prev in Thread] Current Thread [Next in Thread]