From help-octave-request at bevo dot che dot wisc dot edu Wed Feb 25 13:19:53 2004
Subject: Re: bivariate linear Regression with correlated errors
From: Przemek Klosowski <przemek at jazz dot ncnr dot nist dot gov>
To: help-octave at bevo dot che dot wisc dot edu
Date: Wed, 25 Feb 2004 14:18:17 -0500 (EST)


   on 2/25/04 5:55 AM, Andreas Gaab at gaab at mpch-mainz dot mpg dot de wrote:
   ..
   > -my data set is bivariate with highly correlated errors.
   > -I need to calculate a weighted linear regression with a standard error on the slope
   > -wpolyfit.m takes only  dy ...
   > and my knowlege is too small to use basic statistics.

I vaguely remembered that there has been some work on that; I did a search, and 
came up with a direct hit to a reference (see below). Holy Smoke! that was me! 

Note also other articles in this thread:

  http://groups.google.com/groups?threadm=1990Sep3.233745.40%40cunixf.cc.columbia.edu

in particular, the last article by Todd Green, Department of
Chemistry, University of Western Australia <tiq at vaxa dot cc dot uwa dot oz dot au>



    From: Przemek Klosowski (przemek at liszt dot helios dot nd dot edu)
    Subject: Re: Linear regression with weighted x's as well as y's?
    Date: 1990-09-18 05:28:18 PST

     at article{cameron89,
     title="Linear least-squares fits with errors in both coordinates",
     author="B. Cameron Reed",
     journal="Am. J. Phys",
     volume= 57(7)
     month=jul,
     year=1989
    }
    and references therein.

    --
       przemek klosowski (przemek at ndcva dot cc dot nd dot edu)
       Physics Dept
       University of Notre Dame IN 46556



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