From help-octave-request at bevo dot che dot wisc dot edu Fri Jan 17 04:15:15 2003
Subject: Re: How to get Correlation factor?
From: Paul Kienzle <pkienzle at users dot sourceforge dot net>
To: gaab at mpch-mainz dot mpg dot de
Cc: Octave list <help-octave at bevo dot che dot wisc dot edu>
Date: Fri, 17 Jan 2003 05:15:51 -0500

ASG wrote:

>I  have two-dimensional data, which I want to fit with a linear regression. I 
>get nice results with 
>
>[p, yf] = polyfit (x, y, 2)
>
>And now I need the correlation factor...
>Is there a nice way to calculate this?
>
>It would be also quite good, if anybody knows how to calculate the MSWD (Mean 
>Square Weighted Deviation)  for a linear regression?
>
octave-forge/main/optim (http://octave.sf.net) has wpolyfit to do a 
weighted polynomial fit.  It also
returns an error estimate for the parameters.

Paul Kienzle
pkienzle at users dot sf dot net

>  
>




-------------------------------------------------------------
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
-------------------------------------------------------------