Academic article

Combining designed experiments with several blocks of spectroscopic data

Jørgensen, Kjetil; Mevik, Bjørn-Helge; Næs, Tormod

Publication details

Journal: Chemometrics and Intelligent Laboratory Systems, vol. 88, p. 154–1, 2007

Publisher: Elsevier

Issue: 2

International Standard Numbers:
Printed: 0169-7439
Electronic: 1873-3239

Open Access: none

Two varieties of a new method of analysis are introduced and tested against a standard PLS method. The method is developed for situations where experimental design is combined with spectroscopic measurements at several points in an industrial process. The method is a combination of ordinary least squares (OLS) and PLS and is called LS-PLS. The purpose of the methodology is to extract relevant information from spectroscopic measurements without having to calibrate the instrument against external reference measurements first. We compare the LS-PLS variants with a straight forward PLS modeling of all the available variables and demonstrate that the LS-PLS method give results that are easier to interpret, The methods are compared by computer simulations based on real data from a cheese making experiment. (c) 2007 Elsevier B.V. All rights reserved.