Services & Resources / Wolfram Forums
-----
 /
MathGroup Archive
1993
*January
*February
*March
*April
*May
*June
*July
*August
*September
*October
*November
*December
*Archive Index
*Ask about this page
*Print this page
*Give us feedback
*Sign up for the Wolfram Insider

MathGroup Archive 1993

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

Search the Archive

NonlinearFit

  • To: mathgroup at yoda.physics.unc.edu
  • Subject: NonlinearFit
  • From: 4_DKEFFORD at fair1.fairfield.edu
  • Date: 05 Mar 1993 14:17:31 -0500 (EST)

Hello everybody.

Thanks for all your responses- many of you suggested that I use the latest
version of NonlinearFit available as shareware. I git it running and was
able to get it to work for a parabolic and a linear fit with no problems.
However, when I try to do a double exponential fit, which is what I need to
do in the first place, I keep getting the following error:

NonlinearFit::baddata '1' is not a real matrix

I have really no idea why this happens- I'm simply using about 200 points 
generated from a known double exponential, which I created as follows:

silicon=Table[{x,f[x]},{x,-50,450,5}]

where f[x_]=-.2*Exp[-.01*x]+.1*Exp[-.05*x]

Then I run the following:

NonlinearFit[silicon,a*Exp[-b*x]+c*Exp[-d*x],{a,b,c,d},x]

As far as I can see, I do not have any syntax errors or anything else that
springs to the imagination. Any ideas??

I can be reached at either:

4_dkefford at fair1.fairfield.edu      or
dkefford at delphi.com

Thank for your time.

Dan Kefford





  • Prev by Date: Re: Distribute
  • Next by Date: RE: Integrate (deutsch)
  • Previous by thread: ContourSmoothing - changed in v2.1 ?
  • Next by thread: RE: Integrate (deutsch)