MathGroup Archive 1995

[Date Index] [Thread Index] [Author Index]

Search the Archive

Re: Special Nonlinear Fitting?

  • To: mathgroup at smc.vnet.net
  • Subject: [mg2380] Re: Special Nonlinear Fitting?
  • From: Christian.Jost at epc.u-psud.fr (Christian Jost)
  • Date: Tue, 31 Oct 1995 23:21:55 -0500
  • Organization: Universite Paris-Sud XI

In article <471h73$gb3 at ralph.vnet.net>, f91el at efd.lth.se (Erik Lindahl) wrote:

> Hi,
> I need to do a nonlinear fitting of data to a function, where I can't get
> an explicit expression for the functions value.
stuff deleted...
> Is there any procedure capable of this?
> I must be able to enter an equation as the model, and state that "Y" is the
> data value at each point.
> Ideas, anybody?
Just my 0.02$. A straighforward (but surely not very efficient) way is to
define an errorfunction, e.g. the sum of the squared differences of left
side and right side, and then use FindMinimum, minimizing for all the
parameters in your expressions (a, b, etc.), giving an explicit starting
point.
FindMinimum will find the minimum in the local basin of attraction where
you started your search. It is slow, but quite reliable.

Hope that helps, Christian.

Christian Jost, Universit=E9 Paris-Sud XI, Orsay, France
jost at psisun.u-psud.fr


  • Prev by Date: Re: AUTOEXEC and CONFIG for Pentium/75
  • Next by Date: Re: Show In/Out names
  • Previous by thread: AUTOEXEC and CONFIG for Pentium/75
  • Next by thread: Re: Show In/Out names