----- Forwarded message from andrea cardini <[email protected]> -----
Date: Fri, 29 Mar 2013 04:02:11 -0400
From: andrea cardini <[email protected]>
Reply-To: andrea cardini <[email protected]>
Subject: Re: CVA vs DA
To: [email protected]
I fully agree with James' advice.
I'd add that you may want to check whether some
careful dimensionality reduction might help
(i.e., using an appropriate number of PCs in the
DA/CVA, if you have many shape coordinates and
small samples) and also whether sample size
heterogeneity has an impact on your analysis.
After selecting the appropriate number of PCs to
include (many criteria are available), using more
or less PCs and/or including a random subsample
of the largest sample to get a fully balanced
(equal sample size) design might allow you to
explore the sensitivity of your results to these parameters.
PAST can do x-validated CVAs as well as
between-group PCA, as an alternative to CVA
scatterplots to show group differences without
'distorting' the geometry of the shape space.
In the Kovarovic et al.'s paper there's an
additional resampling analysis to estimate the
random chance baseline and confidence interval
for an x-validated classification. Evin et al.
(Journal of Archaeological Science,
http://dx.doi.org/10.1016/j.jas.2012.08.005) is
in a sense a follow up of that paper. The first
author developed an R routine to do the baseline
analysis and I believe this is available upon request.
This is another introductory ref. on DA/CVA, which I really like:
Strauss, R.E., 2010. Discriminating groups of
organisms. In: Ashraf, E. (Ed.), Morphometrics
for Nonmorphometricians. Springer-Verlag Publishers, Berlin, pp. 73e91.
There might be a pdf copy (not 100% sure) in Strauss' webpage.
Cheers
Andrea
At 04:33 29/03/2013, you wrote:
>----- Forwarded message from "K. James Soda" <[email protected]> -----
>
>Date: Thu, 28 Mar 2013 23:32:42 -0400
>From: "K. James Soda" <[email protected]>
>Reply-To: "K. James Soda" <[email protected]>
>Subject: Re: CVA vs DA
>To: [email protected]
>
>Dear Eloise,
>
>Actually, cannonical variance analysis is the
>same as (linear) discriminate analysis, although
>I find that the former term is often used to
>describe the graphical aspects of the
>procedure. There are other types of
>discriminate function analysis, but the only one
>with which I am familiar, quadratic function
>analysis, might be impractical. Here's a quick
>explanation of how they work and
>differ:Â Linear discriminate analysis, in a
>way, tries to draw lines in sample space that
>will separate two or more groups. An unknown
>data point is placed into sample space, and
>classified into whichever group has a mean on
>the same side of the line(s) as the
>unknown. The downside is that linear
>discriminate analysis was developed under the
>assumption that every group has an identical
>covariance structure; if this is not the case,
>the method will not work as well. Quadratic
>discriminate function analysis does the same
>thing as linear discriminate analysis, but
>instead of drawing lines it will draw quadratic
>curves. This means that groups need not have
>identical covariance structures, but, as a
>result, the method involves estimating every
>covariance matrix independently, which requires
>large sample sizes. Unfortunately, what
>constitutes a large sample size depends on the
>number of variables. Since landmark-based
>morphometrics tends to have a large number of
>variables, large sample sizes are hard to come by (though not impossible).
>
>My advice is just to try linear discriminate
>function analysis, and assess how well it
>classifies your teeth using a leave-one-out
>(LOO) cross validation. This article gives a
>good overview of how LOO works and why it is necessary:
>
>Kovarovic, Kris, Leslie C. Aiello, Andrea
>Cardini, and Charles A. Lockwood. 2011.
>“Discriminant function analyses in
>archaeology: are classification rates  too
>good to be true? RID G-9951-2011.†Journal of
>Archaeological Science 38 (11) (November):
>3006-3018. doi:10.1016/j.jas.2011.06.028.
>
>It might take a little bit of programming
>though. If you want it, I can provide you with
>a LOO cross validation routine I wrote for
>linear discriminate function analysis in R. If
>you are dissatisfied with the results, there are
>a great deal more classification methods out
>there. Slice, Naylor, and I (Soda) have a 2013
>SICB abstract on an alternative method, though I
>don't think the abstract has appeared in SICB's
>journal yet. If you can find a copy of the
>conference proceedings, it is in there, though.Â
>
>As far as your question about regression, it may
>not matter that the teeth are different sizes
>unless you are interested in size itself as a
>variable. For example, if you wanted to
>regress shape onto calcium content or something
>to that degree I do not see why you would not be able to.
>
>Long answer to a short question, huh? Hope it was helpful.
>
>James
>
>
>On Thu, Mar 28, 2013 at 10:59 PM,
><<mailto:[email protected]>[email protected]>
>
>wrote:
>
>
>----- Forwarded message from Eloise Cave
><<mailto:[email protected]>[email protected]> -----
>
>Date: Thu, 28 Mar 2013 11:11:43 -0400
>From: Eloise Cave <<mailto:[email protected]>[email protected]>
>Reply-To: <mailto:[email protected]>[email protected]
>Subject: CVA vs DA
>To: <mailto:[email protected]>[email protected]
>
>Greetings,
>I am trying to determine the difference in shape
>in stingray teeth between mating season and non
>mating season. I was wondering which test would
>be best to perform, canonical variate analysis
>or discriminant analysis? Also is regression a
>good idea since I do not have a scale with my
>samples and my samples are different sizes?Â
>
>Thank You,
>Eloise Cave
>Florida Atlantic University
><mailto:[email protected]>[email protected]
>
>
>
>----- End forwarded message -----
>
>
>
>
>
>
>----- 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
Datasets:
http://ads.ahds.ac.uk/catalogue/archive/cerco_lt_2007/overview.cfm#metadata
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 -----
