WilcoxCV (version 1.0-2)

generate.split: Generating random splittings into learning and test data sets

Description

The function generate.split generates niter random splittings into learning and test data sets for use in Monte-Carlo cross-validation (MCCV).

Usage

generate.split(niter,n,ntest)

Arguments

niter

The number of iterations (number of splits into learning and split sets).

n

The total number of observations in the data set.

ntest

The number of observations in the test sets.

Value

A niter x ntest matrix giving the indices of the observations included in the test sets. The i-th row gives the indices of the ntest observations included in the test set for the i-th MCCV iteration.

Details

This function is meant for use in Monte-Carlo cross-validation (MCCV).

References

A. L. Boulesteix (2007). WilcoxCV: an R package for fast variable selection in cross-validation. Bioinformatics 23:1702-1704.

See Also

generate.cv,wilcox.split,wilcox.selection.split

Examples

# load WilcoxCV library
library(WilcoxCV)

# Generate 50 splits with ratio 2:1 for a data set including 90 observations
my.split<-generate.split(niter=50,n=90,ntest=30)