Latent Variable Selection Research Articles

Latent variable selection in partial least squares modelling

Selection of the number of latent variables in partial least squares (PLS) is an important issue in process modelling. In this paper, the Bayesian Information Criterion (BIC) is used to establish a rule for the determination of the number of latent variables. Unlike Wold'sR criterion, where the number of latent variables is determined by the prediction error sum of squares, the philosophy of the BIC rule is based on model accuracy and model parsimony. A simulation study and a practical application are used to demonstrate that BIC is a competitive alternative to Wold's R criterion for latent variable selection in PLS.