Dear Sergey
The covariance matrices are characterizing the *variation* in your sample.
The one for the symmetric component of variation is about the variation
in the averages of the original landmark configurations and their
reflected and relabelled copies. This is what we normally think of as
the variation in the "shape" of things if we are not specifically
interested in asymmetry, e.g. in applications in taxonomy, ecology and
many evolutionary questions.
The covariance matrix for the asymmetry component is about the variation
of asymmetry among specimens -- this is fluctuating asymmetry.
Directional asymmetry is the *mean* asymmetry -- so this is not in
either covariance matrix.
For a recent overview of all this stuff, with many references to other
literature, see this paper:
http://www.mdpi.com/2073-8994/7/2/843
Best wishes,
Chris
On 11/11/2017 14:14, serg bar wrote:
четверг, 18 августа 2016 г., 18:58:47 UTC+3 пользователь serg bar
написал:
I analyzed some population’s oak tree leaves (object asymmetry).
I created covariance symmetrical matrix and matrix of asymmetry in
MorphoJ.
Does symmetrical matrix signalized on directional asymmetry?
If it does, the samples with pure FA (in Procrustes ANOVA , ind *
side) really contain undetected DA in symmetrical matrix?
If it does not, the samples with pure FA contain what?
--
MORPHMET may be accessed via its webpage at http://www.morphometrics.org
---
You received this message because you are subscribed to the Google
Groups "MORPHMET" group.
To unsubscribe from this group and stop receiving emails from it, send
an email to morphmet+unsubscr...@morphometrics.org
<mailto:morphmet+unsubscr...@morphometrics.org>.
--
***********************************
Christian Peter Klingenberg
School of Biological Sciences
University of Manchester
Michael Smith Building
Oxford Road
Manchester M13 9PT
United Kingdom
Web site: http://www.flywings.org.uk
E-mail: c...@manchester.ac.uk
Phone: +44 161 2753899
Skype: chris_klingenberg
***********************************
--
MORPHMET may be accessed via its webpage at http://www.morphometrics.org
---
You received this message because you are subscribed to the Google Groups "MORPHMET" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to morphmet+unsubscr...@morphometrics.org.
