[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: How do you find curvature of "splattered" data?
|
From: |
Keith Goodman |
|
Subject: |
Re: How do you find curvature of "splattered" data? |
|
Date: |
Mon, 13 Mar 2006 14:42:23 -0800 |
On 3/13/06, Robert A. Macy <address@hidden> wrote:
> Quentin,
>
> an arc, hmmm...interesting concept.
>
> But I think what I need is a polynomial fit to splattered
> data.
>
> Where the solution would be a single curved line drawn as a
> "best" fit through the set of data.
>
> The curve can be relative to the center of the data set.
Does b = x\y work? Where the first column of x is ones, the second
column is x, third is x.^2, etc. The noise along the x direction will
shrink the slope b towards zero. That makes sense since in the limit
of infinite x noise (or y noise) you'd expect a slope of zero.
The "best" fit line is x*b.
-------------------------------------------------------------
Octave is freely available under the terms of the GNU GPL.
Octave's home on the web: http://www.octave.org
How to fund new projects: http://www.octave.org/funding.html
Subscription information: http://www.octave.org/archive.html
-------------------------------------------------------------