[Biomod-commits] CurrentPred error

[Viorel Popescu]

Hi everyone,

I am new to BioMod and I have been using the Tutorial as an example to run
some simple preliminary models on my data. Everything went well with
running GLM, GAM and RF: I am getting predictions, I can evaluate variable
importance etc., but when I try to convert back to binary data using
CurrentPred, I get a couple different error messages.

First, when I use all models and binary transformation options I get:

CurrentPred(GAM=T, GLM=T, RF=T, BinRoc=T, BinKappa=T, BinTSS=T, FiltRoc=T,
FiltKappa=T, FiltTSS=T)

Error in apply((x > y), 2, as.integer) :
  (list) object cannot be coerced to type 'integer'
In addition: Warning message:
In sweep(data.matrix(ProbData), 2, CutOffdata, FUN2) :
  length(STATS) or dim(STATS) do not match dim(x)[MARGIN]

Then I try this:

CurrentPred(GAM=T, BinKappa=T)
Error in apply((x > y), 2, as.integer) :
  (list) object cannot be coerced to type 'integer'

Any combinations of models/conversion methods give similar error messages.
I am not sure what the problem is. I can provide more details on the steps
prior to CurrentPred if needed.

Thank you in advance for your help...

Cheers,
Viorel



-- 
Viorel D. Popescu
Postdoc
University of Califonia - Santa Cruz &
Simon Fraser University, Biological Sciences
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/biomod-commits/attachments/20120524/3085732e/attachment.html>