MathGroup Archive 2001

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

Search the Archive

RE: Curve fitting

  • To: mathgroup at smc.vnet.net
  • Subject: [mg29333] RE: [mg29323] Curve fitting
  • From: "Johannes Ludsteck" <johannes.ludsteck at wiwi.uni-regensburg.de>
  • Date: Thu, 14 Jun 2001 02:27:14 -0400 (EDT)
  • Sender: owner-wri-mathgroup at wolfram.com

Dear Tobin,

if you know that the expression in your mail is 
the PDF or CDF of a statistical distribution, you 
should write down the log-likelihood of the 
problem and maximize it with respect to the 
parameters c1,...,c5 using FindMinimum, (i.e. 
minimize the negative of the log-likelihood).

The log likelihood of the dataset is the sum of 
the log of the likelihoods/densities of each 
individual observation.


If you don't know how to set up the maximization  
you could try 


<<<<Statistics`NonlinearFit`


NonlinearRegress[data,

  c1 Exp[x/c2]+c3 Exp[x/c4]+c5,

  x,{c1,c2,c3,c4,c5}]


but this may give inconsistent results.


Best regards,

	Johannes

Johannes Ludsteck
Institut fuer Volkswirtschaftslehre
Lehrstuhl Prof. Dr. Moeller
Universitaet Regensburg
Universitaetsstrasse 31
93053 Regensburg
Tel +49/0941/943-2741



  • Prev by Date: Re: frameticks without numbers
  • Next by Date: Re: how to get an assignment from a rule ?
  • Previous by thread: Curve fitting
  • Next by thread: Re: Curve fitting