Lukas,

Lukas Kohl <llukas.kkohl <at> gmail.com> writes:

> 
> Hello R-list
> 
> Maybe someone knows what's going on here.
> 
> I'm trying to re-run a script I wrote earlier this year using the function
> rda() in the vegan package. The script run fine back then, and I did not
> change the dataset, so I was wandering whether there's some problem in a
> updated version of the package (I re-installed R + all packages since then).
> 
> Thanks for any advice,
> Lukas Kohl
> 

Sorry for the late reply: I don't follow this list regularly.

A couple of points about your question:

(1) vegan indeed has function rda(), but its output has no resemblance
to your example (except for the line repeating Call:). Either you are using
some other package or you have made up your own version of rda() or you
do not show its output.

(2) The rda() function in vegan 2.2-0. This is documented in NEWS. You can
see this by issuing vegandocs("NEWS") command after loading library(vegan).

(3) I have no idea what your script does (id does something different than
vegan::rda()) and I cannot reproduce the problem without that knowledge.

Kind regards, Jari Oksanen
 
PS. Sorry for not top-posting: Gmane does not allow it.

PS2. Sorry for removing some of your message: Gmane requires this.

> --
> 
> So here's the output I get:
> 
> > rda(rel)
> Call:
> rda(X = rel)
> 
> Regularization parameters:
> NULL
> 
> Prior probabilities of groups:
> NULL
> 
> Misclassification rate:
>        apparent:  %
> Warning message:
> In is.na(x$error.rate[1]) :
>   is.na() applied to non-(list or vector) of type 'NULL'
> 
> There's no NA's in my dataset, which seems ok..
> 
> > sum(is.na(rel))
> [1] 0
> > nrow(rel)
> [1] 59
> > ncol(rel)
> [1] 49
> > head(rel)
>       X14.0   i.15.0  ai.15.0    br.16.0      X15.1    n.15.0    i.16.0

______________________________________________
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

Reply via email to