On Wed, 2010-01-20 at 23:28 +0800, Bingzhang Chen wrote:> Hi,
>
> I am stuck in one problem when doing nonmetric multidimensional
> scaling. I use the function 'metaMDS' in the package
'vegan' to work
> on the presence/absence community data. The problem is when two
> samples are identical (dissimilarity = 0), metaMDS cannot work with
> zero dissimilarity.
>
> I don't want to delete the duplicates as they are true samples from
> different locations.
But they *must* be located in the exact same space in the nMDS
solution/plot, so what is the point in having them both in the analysis?
Just adjust the labelling when drawing the nMDS plot so that the single
point gets two labels (which you'll need to do by hand).
The other option is to look at argument 'zerodist' and its description
for details on another way to work round this "problem" --- see
?metaMDS
for details.
I don't recommend the workaround offered with 'zerodist' but you may
have a different opinion on this matter.
HTH
G
>
> Thanks in advance.
>
> Bingzhang Chen
>
>
> ___________________________________________________________
> ?????????????????
> http://card.mail.cn.yahoo.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.
--
%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%
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
%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%