Hi all,
I ran a discriminant analysis with some data and want to get a general idea
of prediction error rate. Some have suggested using X-fold cross validation
procedure. Anyone know if there is a function for this in R?
Thanks,
Wade
[[alternative HTML version deleted]]
how hard is it to write one though?
On 11/16/06, Wade Wall [EMAIL PROTECTED] wrote:
Hi all,
I ran a discriminant analysis with some data and want to get a general idea
of prediction error rate. Some have suggested using X-fold cross validation
procedure. Anyone know if there is a function
Hi, Wade:
Some functions in R have n-fold cv themselves. For example, if you are
looking for a linear discriminant analysis (lda {MASS}), it comes with
a leave-one-out cv in which n equals the size of training sample,
and it gives you pretty good estimation of error rate. But be advised,
this
5350
Woburn, MA 01801
Tel: 781-938-3830
www.nuverabio.com
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Wensui Liu
Sent: Thursday, November 16, 2006 11:37 AM
To: Wade Wall
Cc: r-help@stat.math.ethz.ch
Subject: Re: [R] X-fold cross validation function
@stat.math.ethz.ch
Subject: Re: [R] X-fold cross validation function for discriminant analysis
One option is the Bioconductor package MLInterfaces that provides a unified
interface for several machine learning alrogirithms and methods for
cross-validation etc. See the algorithms web site for details