SELECTIVE IMPROVEMENTS IN MULTIQUALITY PRODUCTS ASSISTED BY ROTATED PRINCIPAL COMPONENTS

Authors
Citation
K. Dyrstad, SELECTIVE IMPROVEMENTS IN MULTIQUALITY PRODUCTS ASSISTED BY ROTATED PRINCIPAL COMPONENTS, Chemometrics and intelligent laboratory systems, 42(1-2), 1998, pp. 115-124
Citations number
9
Categorie Soggetti
Computer Science Artificial Intelligence","Robotics & Automatic Control","Instument & Instrumentation","Chemistry Analytical","Computer Science Artificial Intelligence","Robotics & Automatic Control
ISSN journal
01697439
Volume
42
Issue
1-2
Year of publication
1998
Pages
115 - 124
Database
ISI
SICI code
0169-7439(1998)42:1-2<115:SIIMPA>2.0.ZU;2-E
Abstract
Selective improvements in pharmaceutical multiquality products have be en assisted by rotated principal components. Orthogonal and oblique ro tations of principal components have been applied to evaluate data fro m two production process studies. The purpose of the presented methods is to locate the process variables (X's) that can be used to vary som e quality parameters (Y's), with as minimal influence on other Y's as possible, followed by explicit illustrations of such X-Y relations. Tw o procedures involving varimax rotation are used for this purpose. One , evaluate the loadings from varimax performed on all variables (X's a nd Y's). Two, varimax performed on Y's only, followed by linear regres sion of the varimax Y-scores on X's (VMLR or VPLS) to evaluate the eff ect of X's on certain Y-groups. The VMLR and VPLS were generally found to be more robust methods compared with varimax only. The information derived from the rotation analysis was used to adjust the relevant X- variables in linear regression models developed to estimate precise Y' s. (C) 1998 Elsevier Science B.V. All rights reserved.