Premium
Multiresponse optimization with consideration of probabilistic covariates
Author(s) -
Hejazi T. H.,
Bashiri Mahdi,
Noghondarian Kazem,
Atkinson A. C.
Publication year - 2011
Publication title -
quality and reliability engineering international
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.913
H-Index - 62
eISSN - 1099-1638
pISSN - 0748-8017
DOI - 10.1002/qre.1133
Subject(s) - covariate , nuisance , probabilistic logic , mathematical optimization , econometrics , computer science , statistics , mathematics , political science , law
In many complex experiments, nuisance factor may have large effects that must be accounted for. Covariates are one of the most important kinds of nuisance factors that can be measured but cannot be controlled within the experimental runs. In this paper a novel approach is proposed, based on goal programming, to find the best combination of factors so as to optimize multiresponse‐multicovariate surfaces with consideration of location and dispersion effects. Furthermore, it is supposed that several covariates considered in the experiment have probability distributions of known form. One objective is to find the most probable values of each covariate. For this purpose, a multiobjective mathematical optimization model is proposed and its efficacy is demonstrated by two numerical examples. Copyright © 2010 John Wiley & Sons, Ltd.