SIMPLS algorithm for calibration of PLS model (old version)
pls.simplsold(x, y, ncomp, cv =FALSE)
Arguments
x: a matrix with x values (predictors)
y: a matrix with y values (responses)
ncomp: number of components to calculate
cv: logical, is model calibrated during cross-validation or not
Returns
a list with computed regression coefficients, loadings and scores for x and y matrices, and weights.
References
[1]. S. de Jong. SIMPLS: An Alternative approach to partial least squares regression. Chemometrics and Intelligent Laboratory Systems, 18, 1993 (251-263).