Skip to content
Prev 323581 / 398503 Next

Vegan package treatment of zeros

On Wed, 2013-05-15 at 09:04 -0500, Michael Rentz wrote:
Blanks would be interpreted as `NA` in R when you read the data in.
Vegan would respect that and most likely fail because of the missing
data as not all methods are appropriate when there are `NA` values.

Hence a common first step is to replace `NA` with 0. As you have already
have this indicated in your file external to R then you won;t need to do
this extra step *in* R.

How zeros are then treated will depend largely on the method employed
and/or the dissimilarity coefficient used, but that is not an R
question. A recent posting to the R-Sig-Ecology list by Brian Cade
presents some interesting observations on the double zero issue:

https://stat.ethz.ch/pipermail/r-sig-ecology/attachments/20130419/114d1e5f/attachment.pl

HTH

G