-------- Original Message --------
Subject: Re: Variance explained by size
Date: Mon, 29 Aug 2011 14:21:42 -0400
From: Dennis E. Slice <[email protected]>
To: [email protected]
Shape, by definition, already has isometric size taken out, though the
ghost of size may still be there via allometric components. If you want
to examine isometric+allometric components, then you are interested in
form, not shape. So,
1) SHAPE = f(CS)
2) FORM = f(CS)
The old Morpheus and all of the GRF programs allow you to restore size
(form_i = shape_i*cs_i).
There are cases where this is inadvisable. For instance, PCA, and
Mitteroecker et al. (2004) recommend shape + log(CS) in some form as the
appropriate data (see their appendix for a good discussion of
alternative formulations and justifications). General extensions of
this, called Procrustes size-shape space analysis, are available
in...well, they were in Morphologika. Probably in MorphoJ, now, I would
expect.
-ds
Mitteroecker, P, P Gunz, M Bernhard, K Schaefer, and FL Bookstein. 2004.
“Comparison of cranial ontogenetic trajectories among great apes and
humans.” JOURNAL OF HUMAN EVOLUTION 46 (6) (June): 679-697.
On 8/29/11 2:11 PM, morphmet wrote:
-------- Original Message --------
Subject: Re: Variance explained by size
Date: Mon, 29 Aug 2011 14:06:09 -0400
From: Guilherme Garcia <[email protected]>
To: [email protected]
hi,
with respect to the question, you could simply use the R² of a
multivariate regression over shape variables to get a % of shape
variance explained by isometric variation (centroid size), and that
(shape correlated with CS) would be allometric variation.
but, if I wanted to have a measure of size variation (isometric +
allometric) with respect to the total variation in the system, akin to
the % of variation associated with a particular principal component,
how would I proceed?
more importantly, would this make any sense in a GM context?
thanks in advance,
guilherme.
On Mon, Aug 29, 2011 at 12:44 PM, morphmet
<[email protected]> wrote:
-------- Original Message --------
Subject: Re: Variance explained by size
Date: Mon, 29 Aug 2011 11:44:00 -0400
From: Dennis E. Slice <[email protected]>
To: morphmet <[email protected]>
Without looking at the specific example, it may be worth mentioning that
there are two issues size/shape relationships - isometric and
allometric. GPA removes isometric size variation, but there could still
be an association with size and shape. For instance, maybe all large
specimens were tall, skinny rectangles while all small ones were short,
fat rectangles. Size could, in such a case, "explain" 100% of "pure"
shape variation. -ds
On 8/26/11 5:29 PM, brian boivin wrote:
Hi,
In Geometrics morphometrics for Biologist : A Primer (pg7) it says:"In
the two species mentionned above (in which PC1 accounts for 99.4% of
the variance), SIZE explains 71% of the variance in SHAPE in one
species, but only 21.7% in the other."
I did not find any information in the book to explains the impact of
size on the variance in shape. Did I miss something?
How can one calculate the % of variance in shape explained by size?
Email:[email protected]
Thank you for your time
B.B
--
Dennis E. Slice
Associate Professor
Dept. of Scientific Computing
Florida State University
Dirac Science Library
Tallahassee, FL 32306-4120
-
Guest Professor
Department of Anthropology
University of Vienna
-
Software worth having/learning/using...
Linux (Operating System: Ubuntu, CentOS, openSUSE, etc.)
OpenOffice (Office Suite: http://www.openoffice.org/)
R package (Stats/Graphics environment: http://www.r-project.org/)
Eclipse (Java/C++/etc IDE: http://www.eclipse.org/)
Netbeans (Java/C++/etc IDE: http://netbeans.org/)
Zotero (FireFox bibliographic extension: http://www.zotero.org/)
========================================================
--
Dennis E. Slice
Associate Professor
Dept. of Scientific Computing
Florida State University
Dirac Science Library
Tallahassee, FL 32306-4120
-
Guest Professor
Department of Anthropology
University of Vienna
-
Software worth having/learning/using...
Linux (Operating System: Ubuntu, CentOS, openSUSE, etc.)
OpenOffice (Office Suite: http://www.openoffice.org/)
R package (Stats/Graphics environment: http://www.r-project.org/)
Eclipse (Java/C++/etc IDE: http://www.eclipse.org/)
Netbeans (Java/C++/etc IDE: http://netbeans.org/)
Zotero (FireFox bibliographic extension: http://www.zotero.org/)
========================================================
