[R] What is the default nPerm for regression in randomForest?

Liaw, Andy andy_liaw at merck.com
Thu May 6 15:14:54 CEST 2010


Firstly, you've posted a number of similar messages (not this one, but
about explanation of variable importance) three times since last
evening.  I'd ask that you not bombard the mailing list with the same
messages.  No one on the list is obligated to help you within the time
you seem to expect, and re-posting isn't likely to increase the chance
of getting a useful reply. 

To the point of your question here:  The default values of arguments to
function (if exist) are shown in the "Usage" section.  In this
particular case:

## S3 method for class 'formula':
randomForest(formula, data=NULL, ..., subset, na.action=na.fail)
## Default S3 method:
randomForest(x, y=NULL,  xtest=NULL, ytest=NULL, ntree=500,
             mtry=if (!is.null(y) && !is.factor(y))
             max(floor(ncol(x)/3), 1) else floor(sqrt(ncol(x))),
             replace=TRUE, classwt=NULL, cutoff, strata,
             sampsize = if (replace) nrow(x) else ceiling(.632*nrow(x)),
             nodesize = if (!is.null(y) && !is.factor(y)) 5 else 1,
             maxnodes = NULL,
             importance=FALSE, localImp=FALSE, nPerm=1,
 
Note the end of that last line quoted above.

Andy
 

From: Dimitri Liakhovitski
> 
> Could not find it in ?randomForest.
> Thank you for your help!
> 
> -- 
> Dimitri Liakhovitski
> Ninah.com
> Dimitri.Liakhovitski at ninah.com
> 
> ______________________________________________
> R-help at r-project.org mailing list
> 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.
> 
Notice:  This e-mail message, together with any attachme...{{dropped:11}}



More information about the R-help mailing list