MathGroup Archive 1995

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

Search the Archive

Re: [Q] How to use NonlinearFit[...]

  • To: mathgroup at christensen.cybernetics.net
  • Subject: [mg902] Re: [Q] How to use NonlinearFit[...]
  • From: rubin at msu.edu (Paul A. Rubin)
  • Date: Sun, 30 Apr 1995 03:36:31 -0400
  • Organization: Michigan State University

In article <3n9shi$poj at news0.cybernetics.net>,
   dave at freebucks.feinberg.nwu.edu (David Johnson) wrote:
->
->I have a set of data that I would like to fit to an equation
->using the following initial equation:  x[[n+1] = A x[[n]] ( 1 - B X[[n]])
->This is a typical nonlinear, dynamical equation used in many texts
->as a function that may interate equations to chaotic states.
->
->Several people have suggested I use NonlinearFit in the Nonlinear 
package.
->I haven't any clue how to set up this for NonlinearFit.
->I know I must be missing something simple but how can I use NonlinearFit 
to
->finds the best fit for an equation who's next data point is the result of
->its current fit?  Please excuse my lack of good english communication to 
->communicate what I want, I just hope it's understandable.
->
->Has anyone a suggestion or a Mathematica text reference.
->
Lets say x is a vector of length n containing your data, with the oldest 
observation in x[[1]].  Try something like this (after loading 
NonlinearFit):

 NonlinearFit[ 
   Transpose[ {Drop[ x, -1 ], Drop[ x, 1 ]} ], 
   a z (1 - b z), z, {a, b}
 ]

Your independent and dependent variables are x with the newest respectively 
oldest observations removed.

Paul

**************************************************************************
* Paul A. Rubin                                  Phone: (517) 432-3509   *
* Department of Management                       Fax:   (517) 432-1111   *
* Eli Broad Graduate School of Management        Net:   RUBIN at MSU.EDU    *
* Michigan State University                                              *
* East Lansing, MI  48824-1122  (USA)                                    *
**************************************************************************
Mathematicians are like Frenchmen:  whenever you say something to them,
they translate it into their own language, and at once it is something
entirely different.                                    J. W. v. GOETHE


  • Prev by Date: Re: How to prevent Solve from DSolve?
  • Next by Date: Kernel configuration for DEC Alpha on VMS
  • Previous by thread: [Q] How to use NonlinearFit[...]
  • Next by thread: Options to Power Expand