[R-sig-eco] species score in vegan

[Gavin Simpson]

On Wed, 2010-11-03 at 21:57 -0400, Soumi Ray wrote:
> Hi,
> 
> I am facing a problem with getting the species score while running NMDS in
> vegan. My data structure looks like this:
> 
> ,spa,spb,spc,spd,spe,spf,spf,spg
> 1,214.28,470.63,469.38,1109.22,5708.47,0,2973.86,70.51
> 2,118.29,337.1,465.29,887.01,1600.85,0,62.82,12.54
> 3,0,220.87,699.3,1169.4,1454.49,0,73.8,12.28
> .
> .
> 
> I am using the code:
> 
> nmds<-read.table('book3_vag.csv', header=TRUE, sep=",", row.names=1)
> dis.bray<-vegdist(nmds, method="bray")
> nmds<-metaMDS(dis.bray, k=3, wascores=TRUE)
> 
> But the results are noting giving me the species score:
> Call:
> metaMDS(comm = dis.bray, k = 3, wascores = TRUE)
> Nonmetric Multidimensional Scaling using isoMDS (MASS package)
> Data:     dis.bray
> Distance: bray
> Dimensions: 3
> Stress:     8.498857
> No convergent solutions - best solution after 20 tries
> Scaling: centring, PC rotation
> Species: scores missing
> 
> Could anyone kindly suggest where am I going wrong?

Read ?metaMDS more closesly, especially the information on argument
'comm':
     
Arguments:

    comm: Community data. Alternatively, dissimilarities either as a
          ‘dist’ structure or as a symmetric square matrix.  In the
          latter case all other stages are skipped except random starts
          and centring and pc rotation of axes.

so 'wascores' is ignored because you provided the distance matrix - we
don't have the information on the species to be able to do anything more
than compute a standard nMDS with random starts and rotation of results.

If you do read ?metaMDs you will note that you can provide the community
data and get metaMDS to compute the distance matrix for you. So, this

nmds.res <- metaMDS(nmds, distance = "bray", k = 3, wascores = TRUE)
## or equivalently as "bray" is the default
nmds.res <- metaMDS(nmds, k = 3, wascores = TRUE)

should get what you want.

(Why do your want to overwrite your species data object with the output
from metaMDS?) For example, here is a reproducible example

data(varespec)
set.seed(123)
res <- metaMDS(vegdist(varespec, "bray"), k = 3, wascores = TRUE)
res
res2 <- metaMDS(varespec, distance = "bray", k = 3, wascores = TRUE)
res2

HTH

G

> Thank you
> 
> Soumi
> 
> 	[[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
%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%