Determination of the number of components during mixture analysis using the Durbin-Watson criterion in the Orthogonal Projection Approach and in the SIMPLe-to-use Interactive Self-modelling Mixture Analysis approach

The Orthogonal Projection Approach (OPA) and the SIMPLe-to-use Interactive Self-modelling Mixture Analysis approach (SIMPLISMA) are widely employed during process monitoring to obtain concentration profiles and/or pure spectra of a mixture. In the first step of these methods, it is extremely important to select the right number of components present in the mixture. This selection is not always obvious, and in this paper, the Durbin-Watson criterion was applied to dissimilarity values in OPA and to purity values in SIMPLISMA as a tool for the decision of the number of components. It is shown that this yields more objective results than visual interpretation. (C) 2002 Elsevier Science B.V All rights reserved.