RVAideMemoire (version 0.9-35)

PLSDA.ncomp: Graphical help to number of components selection in PLS-DA

Description

Draw a graph with classification error rate (obtained from cross-validation with the M-fold method) and proportion of intergroup variance explained from one to any possible components included in a given PLS-DA model. This helps to choose the number of components to be kept in the model.

Usage

PLSDA.ncomp(X, Y, pred.method = c("mahalanobis.dist", "centroids.dist", "max.dist"),
  M = 10, nrep = 10)

Arguments

X

numeric matrix of predictors.

Y

a factor giving the class of each individual.

pred.method

prediction method to be applied for PLS-DA cross-validation. Should be a subset of "mahalanobis.dist" (default), "centroids.dist" or "max.dist".

M

the number of folds in the M-fold cross-validation.

nrep

the number of repetitions of the whole procedure in the M-fold cross-validation.

Details

The function emphasizes values obtained with nlev - 1 groups, with nlev being the number of levels of the factor, which is often the optimal number of components to be kept.

See Also

plsda, valid, DA.valid, DA.var

Examples

require(mixOmics)
data(yeast)
X <- t(yeast$data)
Y <- yeast$strain.cond
PLSDA.ncomp(X,Y,M=5,nrep=3)