[R-sig-eco] metaMDS vs. isoMDS for NMDS

[Gavin Simpson]

On Tue, 2011-03-08 at 10:05 -0500, Stephen LeDuc wrote:
> Dear R listserve members,
> 
> Does anyone have any thoughts or advice regarding using "metaMDS" versus
> "isoMDS" functions for conducing NMDS in R?  Is one clearly preferred over
> another?  Please respond directly to me at the email below. Any thoughts
> would be most appreciated!   Best regards, Steve LeDuc

Given that isoMDS() is used internally in metaMDS() (at least for now)
I'm not sure your question has meaning. The best reason for using
metaMDS() is that it provides the infrastructure to do the random starts
and comparison of configurations for convergence out of the box for you.
Even if you turn off all the other helper niceties, the random starts
makes metaMDS() a clear winner. but do realise you are using the same R
function in the end; isoMDS().

HTH

G

> sdleduc at gmail.com
> 
> 	[[alternative HTML version deleted]]
> 
> _______________________________________________
> R-sig-ecology mailing list
> R-sig-ecology at r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-ecology

-- 
%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%
 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
%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%