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

Re: Help fitting Exponential curves

• To: mathgroup at smc.vnet.net
• Subject: [mg28980] Re: [mg28969] Help fitting Exponential curves
• From: Simon Chandler <simon_chandler at agilent.com>
• Date: Thu, 24 May 2001 04:06:57 -0400 (EDT)
• References: <200105230554.BAA01366@smc.vnet.net>
• Sender: owner-wri-mathgroup at wolfram.com

Todd,

> 	I am looking to fit some exponential curves to a form of
> 	P=Po*e^(-K*t) where K and Po are values I need. 

This equation requires some method of non-linear fitting. "Non-linear" in the sense that the function is non-linear with respect to its parameters. Fit[] only works for a model that is a linear combination of the basis functions.

There is a non-linear fitting routine in the Statistics`NonlinearFit` package. I suggest you read the manual to the Standard Add-on Packages.

An even better way of doing non-linear fitting is provided by the Experimental Data Analyst package. See http://www.wolfram.com/products/applications/eda/
I thoroughly recommend this package.

If you want to read about non-linear fitting methods have a look in the classic Numerical Recipies book. See http://www.nr.com/

Hope that help,

Simon

• References:
  • Help fitting Exponential curves
    • From: Todd <tcs3a@virginia.edu>