New Package: ipred - Improved predictors

The package ipred is uploaded to CRAN /src/contrib/Devel. 

The main focus of the package is the calculation of improved predictors 
in classification tasks. Misclassification error can be improved by 
bootstrap aggregated classification trees and/or 
the framework of indirect classification. Furthermore, a unified 
interface for the estimation of misclassification error 
completes the features of ipred.

We try to make the interface as general as possible, however nothing is
carved in stone and suggestions for improvement are very welcome.

The DESCRIPTION file:

Package: ipred
Title: Improved Predictors
Version: 0.4-0
Date: $Date: 2002/03/26 16:29:31 $
Author: Andrea Peters <Andrea.Peters@imbe.imed.uni-erlangen.de> and
  Torsten Hothorn <Torsten.Hothorn@rzmail.uni-erlangen.de>
Maintainer: Andrea Peters <Andrea.Peters@imbe.imed.uni-erlangen.de>
Description: Improved predictive models by direct and indirect
  bootstrap aggregation in classification and regression as well as
  resampling based estimators of prediction error.
Depends: rpart, MASS, mlbench
License: GPL


Best regards,
Andrea Peters

