[R-sig-eco] Simpson dissimilarity in metaMDS (vegan)
Olmo
ulmusnigra at yahoo.es
Sun Jul 21 12:55:13 CEST 2013
Hi Elaine,
There is some information in desingdist which can be of use, cause it
allows you to define new similarity index, there is a warning about
the resources used, it is not very efficient:
http://cc.oulu.fi/~jarioksa/softhelp/vegan/html/designdist.html
I hope it helps a bit.
Olmo.
El Sun, 21 Jul 2013 07:46:42 +0800
Elaine Kuo <elaine.kuo.tw at gmail.com> escribió:
> Hello
>
> I am trying to perform NMDS using metaMDS (vegan).
> However, in the argument of "distance," there is no option for Simpson
> Dissimilarity Index.
>
> Please kindly whether it is necessary to set up the distance argument
> if the distance matrix is produced based on the Simpson Dissimilarity
> Index already.
> If necessary, please kindly advise how to set up the distance
> argement.
>
> Thank you.
>
> The code to produce the matrix is as followed:
> # Compute the Simpson distance matrices for the dataset (3 hr using
> 4GB) library(betapart)
> dist.sim<-beta.pair(dataR, index.family="sor")
> class(dist.sim)
>
> betasim.sim<-dist.sim[["beta.sim"]]
> class(betasim.sim)
>
> Elaine
>
> [[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
More information about the R-sig-ecology
mailing list