----- Forwarded message from andrea cardini <[email protected]> -----
Date: Wed, 15 Jan 2014 06:30:56 -0500
From: andrea cardini <[email protected]>
Reply-To: andrea cardini <[email protected]>
Subject: Re: PCA in R vs RWA in tpsRelW
To: [email protected]
Dear Eugenia,
as far as I know, except if you play with some of
the parameters (alpha, uniform comp. etc. in
TPSRelw) instead of using the default options, a
PCA of Procrustes shape coordinates should
produce identical scores as a RWA in TPSRelw. The
only difference could the sign of the axes, which
is arbitrary (i.e., scatterplots could look flipped in one or more directions).
The method you select to slide the semilandmarks
might have an effect too. You could easily check
if the differences depend on the superimposition
(including the sliding) or the PCA by comparing
the matrices of shape distances (shape coord. in
R vs shape coord. in TPSRelw, PCs in R vs RWs in
TPSRelw and even shape coord. vs PCs or shape
coord. vs RWs within the same software): they
should all be the same and have a matrix correlation of 1.
I've not played with geomorph for a long time.
One year ago, more or less, I had double checked
results in R and TPSRelw, as you did, and they
were virtually identical. However, I think I
compared only shape coordinates. I am not sure if
I checked also PC scores. If the PCA is done in R
but not in geomorph, be careful to select the
right options (variance covariance matrix and
scaling of the axes). Also, there's at least one
of the packages for doing PCAs in R (don't ask me
which one!) which does not like the redundancy in
the data after the superimposition.
If you send me the data, I can give a quick look.
Cheers
Andrea
Delivered-To: [email protected]
X-Received: by 10.224.66.134 with SMTP id n6mr7299163qai.39.1389738164839;
Tue, 14 Jan 2014 14:22:44 -0800 (PST)
Authentication-Results: mx.google.com;
spf=neutral (google.com: 209.235.156.242
is neither permitted nor denied by best guess
record for domain of
[email protected])
[email protected]
Resent-Date: Tue, 14 Jan 2014 17:22:26 -0500
X-Authentication-Warning:
mail102c40.carrierzone.com:
postmaster.morphometrics.org set sender to
[email protected] using -f
Old-X-Envelope-From: [email protected]
From: [email protected]
To: [email protected]
Subject: PCA in R vs RWA in tpsRelW
Date: Tue, 14 Jan 2014 14:22:05 -0800
User-Agent: Webmail 6.0
X-CTCH-RefID:
str=0001.0A020204.52D5B8A2.010E,ss=1,re=0.000,recu=0.000,reip=0.000,cl=1,cld=1,fgs=0
X-CTCH-RefID:
str=0001.0A020207.52D5B88D.005D,ss=1,re=0.000,recu=0.000,reip=0.000,cl=1,cld=1,fgs=0
X-CTCH-VOD: Unknown
X-CTCH-VOD: Unknown
X-CTCH-Spam: Unknown
X-CTCH-Spam: Unknown
X-CTCH-Score: 0.000
X-CTCH-Score: 0.000
X-CTCH-Rules:
X-CTCH-Rules:
X-CTCH-Flags: 0
X-CTCH-Flags: 0
X-CTCH-ScoreCust: 0.000
X-CTCH-ScoreCust: 0.000
X-WHL: LR
Resent-From: [email protected]
Reply-To: [email protected]
X-Mailing-List: <[email protected]> archive/latest/1909
X-Loop: [email protected]
List-Post: <mailto:[email protected]>
List-Help: <mailto:[email protected]?subject=help>
List-Subscribe: <mailto:[email protected]?subject=subscribe>
List-Unsubscribe:
<mailto:[email protected]?subject=unsubscribe>
Resent-Sender: [email protected]
X-Antivirus: avast! (VPS 140114-1, 14/01/2014), Inbound message
X-Antivirus-Status: Clean
----- Forwarded message from Eugenia Gold <[email protected]> -----
Date: Tue, 14 Jan 2014 16:12:12 -0500
From: Eugenia Gold <[email protected]>
Reply-To: Eugenia Gold <[email protected]>
Subject: PCA in R vs RWA in tpsRelW
To: "[email protected]" <[email protected]>
Hi everyone!
I'm working on a project in which I use sliding
semilandmarks. I've run the dataset through the
tpsRelW software and through R using the geomorph
package, but I get different results using each.
I've fixed the slider file to allow for sliding
semilandmarks in geomorph. My understanding is
the RWA is equivalent to PCA, so would there be a
difference in a PC1vPC2 versus a RW1vRw2 plot?
Thanks for the help!
-Eugenia
M. Eugenia L. Gold
Doctoral Candidate
Richard Gilder Graduate School
Division of Paleontology
American Museum of Natural History
New York, NY 10024
----- End forwarded message -----
Dr. Andrea Cardini
Researcher in Animal Biology, Dipartimento di
Scienze Chimiche e Geologiche, Università di
Modena e Reggio Emilia, l.go S. Eufemia 19, 41121 Modena, Italy
Honorary Fellow, Centre for Anatomical and Human
Sciences, University of Hull, Cottingham Road,
Hull, HU6 7RX, UK & University of York, Heslington, York YO10 5DD, UK
Adjunct Associate Professor, Centre for Forensic
Science , The University of Western Australia, 35
Stirling Highway, Crawley WA 6009, Australia
E-mail address: [email protected], [email protected]
WEBPAGE: http://sites.google.com/site/hymsfme/drandreacardini
Summary of research interests at:
http://www.dscg.unimore.it/site/home/ricerca/aree-di-ricerca/evolution-taxonomy-and-forensics.html
FREE Yellow BOOK on Geometric Morphometrics:
http://www.italian-journal-of-mammalogy.it/issue/view/405
or full volume at:
http://www.italian-journal-of-mammalogy.it/public/journals/3/issue_241_complete_100.pdf
Editorial board for:
Zoomorphology:
http://www.springer.com/life+sciences/animal+sciences/journal/435
Journal of Zoological Systematics and
Evolutionary Research: http://www.wiley.com/bw/journal.asp?ref=0947-5745&site=1
Hystrix, the Italian Journal of
Mammalogy: http://www.italian-journal-of-mammalogy.it/
----- End forwarded message -----
