cvOPLSDA: K-fold cross-validation for OPLS-DA.
In ManonMartin/MBXUCL: R Routines for metabolomic data

Description Usage Arguments Value Examples

K-fold cross-validation for OPLS-DA based on the RMSE criterion and stratified according to y.

1	cvOPLSDA(x, y, k_fold = 10, NumOrtho = 1, ImpG = FALSE)

`x`	A data matrix on which will be based the analysis.
`y`	A numerical vector representing the class of individuals.
`k_fold`	The number of sub-datasets to create for cross-validation.
`NumOrtho`	The maximum number of orthogonal components allowed in OPLSDA.
`ImpG`	If `TRUE`, prints a validation plot.

A list with the following elements:

RMSECV: RMSECV from the OPLSDA cross-validation.
folds_i: A vector indicating the group of observations for cross-validation.
Prop1: Table of proportions of 1's in y for each subgroup.
yres: List with true and predicted classes for each NumOrtho.

data('DataSimul')
x = DataSimul[['x']]
y = DataSimul[['y']]
cvOPLSDA.res = cvOPLSDA(x = x, y = y, k_fold = 10, NumOrtho = 5)
plot(cvOPLSDA.res$RMSECV)