[R] Mantel test

[Gavin Simpson]

On Mon, 2009-09-14 at 23:46 -0700, swertie wrote:
> oh yes of course. It is quite simple. I have two presence/absence matrices
> (one for plants, one for butterflies) and I would like to test if the
> butterfly community similarities is correlated with the plant community
> similarities. The think is also that I don't really see the purpose of doing
> a PCA, that's why I would have make the Mantel test directly from the
> distance matrices

I don't know to what specifically (papers?) you are referring in regards
to PCA before Mantel, but as PCA is a dimension reduction technique
which extracts axes of greatest variation, I might hazard a guess that
this is done to focus the Mantel test on the similarity between the two
communities in the main pattern of variation within each community.

If that is why this was done, there are better ways of extracting common
patterns (e.g. coinertia analysis and co-correspondence analysis) from
two community matrices. You should not expect PCA1 of butterflies to be
related to PCA1 of plants for example, it could be related to PC3-5 of
plants. Both the techniques I mention allow you to get the "answer" with
a single analysis - if that is why PCA before Mantel was being
performed.

See the Environmetrics Task View on CRAN for details of which packages
contain the two methods I mention.

You might get more traction if you post in the R-SIG-Ecology list.

HTH

G

> 
> 
> 
> Tal Galili wrote:
> > 
> > Hi swertie ,
> > Could you please add more details ?
> > What field are you at, some links maybe ?
> > 
> > Thanks,
> > Tal
> > 
> > 
> > 
> > 
> > 
> > On Mon, Sep 14, 2009 at 8:30 PM, swertie <v_coudrain at voila.fr> wrote:
> > 
> >>
> >> Hello! It is not really linked to R, but can somebody explain me why we
> >> sometimes make a mantel test directly for to distance matrices and
> >> sometimes
> >> we first make a gradient analysis and then a mantel test between the
> >> axis?
> >> Thank you
> >> --
> >> View this message in context:
> >> http://www.nabble.com/Mantel-test-tp25439984p25439984.html
> >> Sent from the R help mailing list archive at Nabble.com.
> >>
> >> ______________________________________________
> >> R-help at r-project.org mailing list
> >> https://stat.ethz.ch/mailman/listinfo/r-help
> >> PLEASE do read the posting guide
> >> http://www.R-project.org/posting-guide.html
> >> and provide commented, minimal, self-contained, reproducible code.
> >>
> > 
> > 
> > 
> > -- 
> > ----------------------------------------------
> > 
> > 
> > My contact information:
> > Tal Galili
> > Phone number: 972-50-3373767
> > FaceBook: Tal Galili
> > My Blogs:
> > http://www.r-statistics.com/
> > http://www.talgalili.com
> > http://www.biostatistics.co.il
> > 
> > 	[[alternative HTML version deleted]]
> > 
> > ______________________________________________
> > R-help at r-project.org mailing list
> > https://stat.ethz.ch/mailman/listinfo/r-help
> > PLEASE do read the posting guide
> > http://www.R-project.org/posting-guide.html
> > and provide commented, minimal, self-contained, reproducible code.
> > 
> > 
> 
-- 
%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%
 Dr. Gavin Simpson             [t] +44 (0)20 7679 0522
 ECRC, UCL Geography,          [f] +44 (0)20 7679 0565
 Pearson Building,             [e] gavin.simpsonATNOSPAMucl.ac.uk
 Gower Street, London          [w] http://www.ucl.ac.uk/~ucfagls/
 UK. WC1E 6BT.                 [w] http://www.freshwaters.org.uk
%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%