-------- Original Message --------
Subject: Re: question about Regression in MorphoJ
Date: Mon, 21 Nov 2011 14:38:37 -0500
From: Chris Klingenberg <[email protected]>
Reply-To: [email protected]
Organization: University of Manchester
To: [email protected]

Dear Paola

The regression score is computed as the projection of the data points
onto the vector of regression coefficient, and a separate one is
provided for each independent variable 9if there are two or more).

In your example, there is only one independent variable, centroid size.
So the regression score (forget about the number 1; there's only one) is
the shape variable that is best related to centroid size ("best" linear
fit in the sense of the least-squares optimisation used in regression).
It is useful to see the trend in the data, check for groupings etc.

For more details on the regression score, see
Drake, A. G., and C. P. Klingenberg. 2008. The pace of morphological
change: historical transformation of skull shape in St. Bernard dogs.
Proceedings of the Royal Society of London, B Biological Sciences 275:71–76.
PDF at http://www.flywings.org.uk/PDF%20files/ProcRSoc2008.pdf

***

The percetage of the Procrustes sums of squares predicted by the
regression ("% predicted:" in the text output) is similar to an
r-squared value.

I hope this helps.

Best wishes,
Chris




On 11/21/2011 7:20 PM, morphmet wrote:


-------- Original Message --------
Subject: question about Regression in MorphoJ
Date: Sun, 20 Nov 2011 07:21:59 -0500
From: Paola Nicolosi <[email protected]>
Reply-To: Paola Nicolosi <[email protected]>
To: [email protected] <[email protected]>, morphomet
<[email protected]>



Hallo to everybody! I would like to know what is the 'Regression score
1' in the graph shape/size doing a Regression between Procrustes
coordinates (Dependent variables) and CS (indipendent variables) when
using MorphoJ with 2D data. And also how to obtain the r value to
evaluate the regression?
Thank you in advance,
paola


--
***************************************************************
Christian Peter Klingenberg
Faculty of Life Sciences
The University of Manchester
Michael Smith Building
Oxford Road
Manchester M13 9PT
United Kingdom

Telephone: +44 161 275 3899
Fax: +44 161 275 5082
E-mail: [email protected]
Web: http://www.flywings.org.uk
Skype: chris_klingenberg
***************************************************************


Reply via email to