A Bayesian approach for multiple response surface optimization in the presence of noise variables

Guillermo Miró-Quesada, Enrique Del Castillo, John J. Peterson

Research output: Contribution to journalArticle

55 Citations (Scopus)

Abstract

An approach for the multiple response robust parameter design problem based on a methodology by Peterson (2000) is presented. The approach is Bayesian, and consists of maximizing the posterior predictive probability that the process satisfies a set of constraints on the responses. In order to find a solution robust to variation in the noise variables, the predictive density is integrated not only with respect to the response variables but also with respect to the assumed distribution of the noise variables. The maximization problem involves repeated Monte Carlo integrations, and two different methods to solve it are evaluated. A Matlab code was written that rapidly finds an optimal (robust) solution in case it exists. Tivo examples taken from the literature are used to illustrate the proposed method.

Original languageEnglish (US)
Pages (from-to)251-270
Number of pages20
JournalJournal of Applied Statistics
Volume31
Issue number3
DOIs
StatePublished - Apr 1 2004

Fingerprint

Multiple Responses
Response Surface
Bayesian Approach
Optimization
Robust Parameter Design
Predictive Density
Monte Carlo Integration
MATLAB
Methodology
Response surface
Bayesian approach

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

@article{d59a25eceace4c0fbbb6c6c5608d820f,
title = "A Bayesian approach for multiple response surface optimization in the presence of noise variables",
abstract = "An approach for the multiple response robust parameter design problem based on a methodology by Peterson (2000) is presented. The approach is Bayesian, and consists of maximizing the posterior predictive probability that the process satisfies a set of constraints on the responses. In order to find a solution robust to variation in the noise variables, the predictive density is integrated not only with respect to the response variables but also with respect to the assumed distribution of the noise variables. The maximization problem involves repeated Monte Carlo integrations, and two different methods to solve it are evaluated. A Matlab code was written that rapidly finds an optimal (robust) solution in case it exists. Tivo examples taken from the literature are used to illustrate the proposed method.",
author = "Guillermo Mir{\'o}-Quesada and {Del Castillo}, Enrique and Peterson, {John J.}",
year = "2004",
month = "4",
day = "1",
doi = "10.1080/0266476042000184019",
language = "English (US)",
volume = "31",
pages = "251--270",
journal = "Journal of Applied Statistics",
issn = "0266-4763",
publisher = "Routledge",
number = "3",

}

A Bayesian approach for multiple response surface optimization in the presence of noise variables. / Miró-Quesada, Guillermo; Del Castillo, Enrique; Peterson, John J.

In: Journal of Applied Statistics, Vol. 31, No. 3, 01.04.2004, p. 251-270.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A Bayesian approach for multiple response surface optimization in the presence of noise variables

AU - Miró-Quesada, Guillermo

AU - Del Castillo, Enrique

AU - Peterson, John J.

PY - 2004/4/1

Y1 - 2004/4/1

N2 - An approach for the multiple response robust parameter design problem based on a methodology by Peterson (2000) is presented. The approach is Bayesian, and consists of maximizing the posterior predictive probability that the process satisfies a set of constraints on the responses. In order to find a solution robust to variation in the noise variables, the predictive density is integrated not only with respect to the response variables but also with respect to the assumed distribution of the noise variables. The maximization problem involves repeated Monte Carlo integrations, and two different methods to solve it are evaluated. A Matlab code was written that rapidly finds an optimal (robust) solution in case it exists. Tivo examples taken from the literature are used to illustrate the proposed method.

AB - An approach for the multiple response robust parameter design problem based on a methodology by Peterson (2000) is presented. The approach is Bayesian, and consists of maximizing the posterior predictive probability that the process satisfies a set of constraints on the responses. In order to find a solution robust to variation in the noise variables, the predictive density is integrated not only with respect to the response variables but also with respect to the assumed distribution of the noise variables. The maximization problem involves repeated Monte Carlo integrations, and two different methods to solve it are evaluated. A Matlab code was written that rapidly finds an optimal (robust) solution in case it exists. Tivo examples taken from the literature are used to illustrate the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=11144355804&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=11144355804&partnerID=8YFLogxK

U2 - 10.1080/0266476042000184019

DO - 10.1080/0266476042000184019

M3 - Article

AN - SCOPUS:11144355804

VL - 31

SP - 251

EP - 270

JO - Journal of Applied Statistics

JF - Journal of Applied Statistics

SN - 0266-4763

IS - 3

ER -