Re: FindFit in 6.0
- To: mathgroup at smc.vnet.net
- Subject: [mg79338] Re: FindFit in 6.0
- From: Jean-Marc Gulliet <jeanmarc.gulliet at gmail.com>
- Date: Wed, 25 Jul 2007 02:03:46 -0400 (EDT)
- Organization: The Open University, Milton Keynes, UK
- References: <f84j65$poh$1@smc.vnet.net>
Dana DeLouis wrote:
> Would like to check w/ others.
> If I use FindFit, and use a "dummy" Method, I'm given a list of the valid
> available methods: Here's my error output:
>
> FindFit::bdmtd: Value of option Method -> dummy is not Automatic, \
> "Gradient", "ConjugateGradient", "InteriorPoint", "QuasiNewton", \
> "Newton", "NMinimize", or "LevenbergMarquardt". >>
>
> Hmm. "InteriorPoint" sounds interesting.
> However, this crashes my Kernal quickly.
> Was wondering if it happens to others.
>
> FindFit[
> {9, 18, 31, 48},
> a*x^2 + b x + c,
> {a, b, c},
> x,
> Method -> InteriorPoint]
>
> We note that both "InteriorPoint" & "NMinimize" are not listed in Help for
> "FindFit."
> But the Help files in 6.0 are so poorly written that it's hard to tell.
> Method->NMinimize doesn't crash my kernal.
>
> A correct/wrong method shouldn't crash the kernel, right?
>
> Thanks for any insight.
> Using 6.0, (trying)
> Using 5.2 Help files
> Studying 4.0 Book.
Hi Dana,
My kernel crashes too (Mathematica 6.0.1 Windows XP SP2).
Regards,
Jean-Marc