MathGroup Archive 2004

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

Search the Archive

Re: Constraints to parameters in FindFit?

  • To: mathgroup at smc.vnet.net
  • Subject: [mg51222] Re: [mg51200] Constraints to parameters in FindFit?
  • From: "Janos D. Pinter" <jdpinter at hfx.eastlink.ca>
  • Date: Sat, 9 Oct 2004 04:18:35 -0400 (EDT)
  • References: <200410080654.CAA24958@smc.vnet.net>
  • Sender: owner-wri-mathgroup at wolfram.com


Jill Foley, PhD
Princeton Plasma Physics Lab
tel. (609) 243-0000
fax (609) 243- 0000
E-mail: <efoley at princeton.edu>


Jill,

You should use NMinimize, or one of the third party optimization packages, 
instead of FindFit (an unconstrained local optimizer). In the fcts and 
packages referred to, you can specify constraints on the dec vars.

I am the principal developer of MathOptimizer and MathOptimizer 
Professional: you can see those at WR's site, also directly available from 
my company. For theoretical background, please see my book 'Global 
Optimization in Action' as well as my more recent papers.

Best regards,
Janos
_________________________________________________

Janos D. Pinter, PhD, DSc
President & Research Scientist, PCS Inc.
Adjunct Professor, Dalhousie University

129 Glenforest Drive, Halifax, NS, Canada B3M 1J2
Telephone: +1-(902)-443-5910
Fax: +1-(902)-431-5100; +1-(902)-443-5910
E-mail: jdpinter at hfx.eastlink.ca
Web: www.pinterconsulting.com     www.dal.ca/~jdpinter
Software products: http://www.pinterconsulting.com/Software_Sum_Info.pdf


At 03:54 AM 10/8/2004, Jill Foley wrote:

>Hi All,
>
>I am using FindFit to fit a series of peaks to some data. I would like
>to be able to constrain some of the parameters of my fit to correspond
>to physical reality. For example, some peaks should have a negative
>amplitude, others positive, where the amplitudes are the parameters
>that Mathematica is finding in FindFit. The peaks are all very near
>each other, so without any constraint, it is making the wrong ones
>negative. I'd like to specify that a given parameter should always be
>negative. I am already giving an initial guess of the proper sign, but
>it doesn't fix the problem.
>
>Please advise - Thanks!
>
>Jill.



  • Prev by Date: Re: Re: Conveniently Restarting Notebooks
  • Next by Date: Re: normal distribution random number generation
  • Previous by thread: Constraints to parameters in FindFit?
  • Next by thread: Re: Constraints to parameters in FindFit?