Re: Levenberg-Marquardt ?
- To: mathgroup at smc.vnet.net
- Subject: [mg23770] Re: Levenberg-Marquardt ?
- From: Jens-Peer Kuska <kuska at informatik.uni-leipzig.de>
- Date: Sat, 10 Jun 2000 02:59:16 -0400 (EDT)
- Organization: Universitaet Leipzig
- References: <8hfddu$hgp@smc.vnet.net>
- Sender: owner-wri-mathgroup at wolfram.com
Hi, Statistics`NonlinearFit`NonlinearFit[] has it, as one of the possible build in methods. Here is the text from the Help-Notebook: "NonlinearFit and NonlinearRegress use FindMinimum to find parameter estimates, thus both functions accept the FindMinimum options AccuracyGoal, Compiled, Gradient, MaxIterations, Method, PrecisionGoal, and WorkingPrecision. The Method option allows you to choose between algorithms for performing the minimization of the \!\(TraditionalForm\`\[Chi]\^2\) merit function. The LevenbergMarquardt method gradually shifts the search for the minimum of \!\(TraditionalForm\`\[Chi]\^2\) from steepest descent to quadratic minimization. Other possible settings for Method are Gradient (steepest descent), Newton, QuasiNewton, and Automatic. The Automatic method does linear fitting for linear models and LevenbergMarquardt search for nonlinear models, thus the meaning of the automatic method differs between NonlinearFit (or NonlinearRegress) and FindMinimum." Regards Jens Alastair McLean wrote: > > Has the Levenberg-Marquard method of non-linear least > squares minimisation been implemented as a Mathematica > function or package yet ? > > Alastair McLean > mclean at physics.queensu.ca