[R] Vegan vegdist Jaccard matrix problem

Jari.Olsanen jari.oksanen at oulu.fi
Mon Sep 24 07:19:09 CEST 2012


kbannarm <kbannarm <at> hotmail.com> writes:

> 
> This is my script:
> 
> Madr<-read.csv("MadRegSppSite.csv", sep=",", row.names=1)
> rownames(Madr) <- Madr[,1]
> Madr <- Madr[,-1] 
> MadrJaccard<-vegdist(Madr, method="jaccard",binary=FALSE)
> MadrJaccard<-as.matrix(dist(MadrJaccard))
> write.table(MadrJaccard,file="MadrJaccard.csv",sep=",",row.names=T)
> 
> The input file is a binary matrix of presence absence of species organized
> in rows, and sites in the first column. 
> The script is running fine but when I open it in excel (MadrJaccard) the
> Jaccard values are between 0 and 4 when the range of values is only supposed
> to be between 0 and 1.
> 
> I cannot figure out what is going on, does anyone have any ideas?
> 

You should carefully re-read yout script. 

The key line contains dist(MadrJaccard) which calculates Euclidean
distances of Jaccard dissimilarities. Do not calculate metadistances.

Cheers, Jari Oksanen




More information about the R-help mailing list