Dear List,
I am investigating shape variation in the carapace of Antarctic krill.
In short - I have 17 samples of krill from 4 surveys in different
regions of Antarctica. The acquisition of these samples was very
opportunistic so I do not have replicate samples either within or
between surveys. Additionally, the samples have varying numbers of
individuals and sex-ratios. Krill have a circumpolar distribution and
the distances between the samples ranges from 50km (within survey) to
5000 km (between survey). I have established that there are 4
morphologies/shapes in krill: female, mature male, immature male and
juvenile.
My research questions is: Are krill from different regions of
Antarctica different shapes? Or more specifically - are krill from near
samples more similar than krill from samples far apart?
To address this question I have:
1. used non-parametric multidimensional scaling (MDS) with the PWS to
create ordinations for each different group (female, mature/immature
males, juvs). I have then labelled the points within the ordination
according to the categorical variables sample or survey. These
ordinations look very similar to the RWS1 v RWS2 from Tps Regr.
2. calculated the similarity (R) between the fields of points using
ANOSIM. Further, I have regressed the similarity index (R) against
distance to see whether samples that are far apart are more different
than samples close together.
My rationale for using MDS instead of PCA is (1) uneven sample sizes /
missing data, (2) lack of replicate samples, (3) a more general interest
in overall patterns/distributions in the data.
My question to you all is:
(1) Can I use non-parametric multivariate techniques
such as MDS or ANOSIM with the Partial warp scores (PWS)?
(2) Given the disfunctional nature of my data are other
approaches suitable?
I havent seen a morphometrics paper that deals with non-parametric
multivariate analysis of shape data. Any references would be
appreciated.
Regards
Luke Finley
PhD candidate
Australian Antarctic Division
And
The University of Melbourne
email: [EMAIL PROTECTED] or straight to list.
___________________________________________________________________________
Australian Antarctic Division - Commonwealth of Australia
IMPORTANT: This transmission is intended for the addressee only. If you are not
the
intended recipient, you are notified that use or dissemination of this
communication is
strictly prohibited by Commonwealth law. If you have received this transmission
in error,
please notify the sender immediately by e-mail or by telephoning +61 3 6232
3209 and
DELETE the message.
Visit our web site at http://www.aad.gov.au/
___________________________________________________________________________
--
Replies will be sent to the list.
For more information visit http://www.morphometrics.org
