[Date Index] [Thread Index] [Author Index]

Re: Finding Regression Coefficient

• To: mathgroup at christensen.cybernetics.net
• Subject: [mg1200] Re: Finding Regression Coefficient
• From: Andreas Fischer <w81b8512 at infosrv.RZ.UniBw-Muenchen.de>
• Date: Tue, 23 May 1995 02:17:33 -0400
• Organization: University of the Federal Armed Forces Munich

tesch at titan.oit.umass.edu (Ralf Tesch) wrote:
>Hi there,
>
>being one of the many people having questions about NonlinearFit[], mine 
>is about finding the regression coefficient r^2 of the solution given by 
>Mma. 
>There is no hint in the Standard Packages Manual (at least I didn't find 
>any...)
>Is there a way implemented in Mma or is that coefficient to be calculated 
>seperately - how???
>Thanks for help
>
>Ralf
>
>____________________________________________
>Ralf Tesch
>Department of Food Science
>Univ. of Mass., Amherst
>tesch at ipo.umass.edu
>
I think it is not allowed to compute r^2, because this coefficient 
(BRAVAIS-PEARSON correlation coefficient) is only appropriate for linear 
regressions. A high r or r^2 doesn't tell anything about the correlation 
between x and y if you assume a nonlinear function between them.
If I am wrong with this or if someone knows a nonlinear regression 
coefficient, please let me know.

Andreas Fischer
University of Armed Forces 
Munich, Germany
andreas.fischer at rz.unibw-muenchen.de