A multiobjective, optimization-based approach for finding latent explanator
y variables for linear models is presented. The best choice of a set of lat
ent explanatory variables is made by minimizing a user-specified combinatio
n of criteria. In this paper, three criteria are used: (i) the data matrix-
related residue, (ii) the observation- or measurement-related residue and (
iii) the condition number of the new data matrix of the latent explanatory
variables. Successful application of the proposed technique toward identifi
cation of a multivariable pilot-scale plans is presented. The proposed algo
rithm is compared with the well-known PLS algorithm, and the result shows t
hat the proposed algorithm is better than the PLS algorithm. Copyright (C)
2000 John Wiley & Sons, Ltd.