wilcox.split computes the Wilcoxon rank sum statistic for all
niter CV or MCCV iterations defined by the matrix
- a numeric vector of length n giving the expression levels of a gene for the n arrays.
- a vector of length n giving the class membership for the n arrays.
ycan be either a factor or a numeric and must be coded as 0,1.
ntestmatrix giving the indices of the
ntestobservations included in each of the
nitertest sets, as generated by the functions
generate.cv. The i-th row of
splitgives the indices of the observations included in the test data set for the i-th iteration.
algo="new", the new fast method described in Boulesteix (2007) is used to compute the Wilcoxon rank statistic. If
algo="naive", the Wilcoxon rank sum statistics are obtained by running the function
The Wilcoxon rank sum statistic is defined as the sum of the X-ranks of the observations with
y=0. The Wilcoxon rank sum test is equivalent to the Mann-Whitney test. It is implemented in the function
In the context of cross-validation (CV) or Monte-Carlo cross-validation (MCCV),
wilcox.selection.split computes the Wilcoxon rank sum statistic for each iteration. At each iteration, a subset of the
n observations is excluded from the data set and considered as test data set. The indices of the observations considered as test set for each of the
niter iterations are given in the
A list with the following components:
- a numeric vector of length
niterwhose i-th component gives the Wilcoxon rank sum statistic obtained in the i-th iteration.
A. L. Boulesteix (2007). WilcoxCV: an R package for fast variable selection in cross-validation. Bioinformatics 23:1702-1704.
# load WilcoxCV library library(WilcoxCV) # Generate data x<-rnorm(100) y<-sample(c(0,1),100,replace=TRUE) # Generate 50 MCCV splits with ratio 2:1 for a data set including 90 observations my.split<-generate.split(niter=50,n=90,ntest=30) # Compute the Wilcoxon rank sum statistic for the 50 iterations. wilcox.split(x=x,y=y,split=my.split,algo="new")
Documentation reproduced from package WilcoxCV, version 1.0-2. License: GPL (>= 2)