Mathematica 9 is now available
Services & Resources / Wolfram Forums
-----
 /
MathGroup Archive
2002
*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 2002

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

Search the Archive

Nonlinear Regression model

  • To: mathgroup at smc.vnet.net
  • Subject: [mg32303] Nonlinear Regression model
  • From: romoscanu at imes.mavt.ethz.ch (Ioan Alexandre Romoscanu)
  • Date: Sat, 12 Jan 2002 05:18:14 -0500 (EST)
  • Sender: owner-wri-mathgroup at wolfram.com

Hello

I have a question about the 

NonlinearRegress[Data, Model, Variables,Parameters] 

function in Mathematica. 

The function is supoosed to find parameters, for given Model, which
best fit the submitted data set.

Can the *model* itself be of a *numerical* nature? In other words, can
the model be smth like

Model[xstart_,theta1_,theta2_]=Findroot[function[x,theta1,theta2]==0,{x,start}]

It seems that this does not work, although it should(?) if one
supplies the Parameters to NonlinearRegress in the form
{theta1,{thetastart1, thetastart2}}, so that no symbolic derivatives
are looked for.

Thanks

AIR


  • Prev by Date: Re: arguments/realtime3d
  • Next by Date: Re: No Subject
  • Previous by thread: Re: Front-End
  • Next by thread: Re: No Subject