Interaction models as alternatives to low-order polynomials

John A. Cornell, Douglas Montgomery

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

One of the most popular classes of models that people fit empirically to data is the class of polynomials. One reason for this is, over limited-sized regions of interest, lower-degree polynomials (specifically, degrees 1, 2, and at most 3) have stood the test of time by proving their versatility when it comes to fitting a wide variety of different surface shapes. However, when faced with modeling a surface over an experimental region whose boundaries extend beyond some localized neighborhood or limited-sized region of interest, a polynomial of degree 2, or even of degree 3, may not be adequate. For this situation we propose fitting an interaction model which is a reduced form of a higher-degree polynomial. Several examples of actual experiments are presented to illustrate the improvement in fit by an interaction model over that of a standard polynomial, even for response surfaces with uncomplicated shapes.

Original languageEnglish (US)
Pages (from-to)163-176
Number of pages14
JournalJournal of Quality Technology
Volume28
Issue number2
StatePublished - Apr 1996

Fingerprint

Polynomials
Polynomial
Alternatives
Region of Interest
Interaction
Order of a polynomial
Response Surface
Model
Modeling
Experiment
Experiments
Class
Standards
Form

Keywords

  • Factorial Design
  • Interactions
  • Lack of Fit
  • Misspecified Model
  • Polynomial Model
  • Response Surface Methodology

ASJC Scopus subject areas

  • Management Science and Operations Research
  • Industrial and Manufacturing Engineering
  • Statistics and Probability

Cite this

Interaction models as alternatives to low-order polynomials. / Cornell, John A.; Montgomery, Douglas.

In: Journal of Quality Technology, Vol. 28, No. 2, 04.1996, p. 163-176.

Research output: Contribution to journalArticle

@article{573ea391c0904cc18b9a4f8bad772808,
title = "Interaction models as alternatives to low-order polynomials",
abstract = "One of the most popular classes of models that people fit empirically to data is the class of polynomials. One reason for this is, over limited-sized regions of interest, lower-degree polynomials (specifically, degrees 1, 2, and at most 3) have stood the test of time by proving their versatility when it comes to fitting a wide variety of different surface shapes. However, when faced with modeling a surface over an experimental region whose boundaries extend beyond some localized neighborhood or limited-sized region of interest, a polynomial of degree 2, or even of degree 3, may not be adequate. For this situation we propose fitting an interaction model which is a reduced form of a higher-degree polynomial. Several examples of actual experiments are presented to illustrate the improvement in fit by an interaction model over that of a standard polynomial, even for response surfaces with uncomplicated shapes.",
keywords = "Factorial Design, Interactions, Lack of Fit, Misspecified Model, Polynomial Model, Response Surface Methodology",
author = "Cornell, {John A.} and Douglas Montgomery",
year = "1996",
month = "4",
language = "English (US)",
volume = "28",
pages = "163--176",
journal = "Journal of Quality Technology",
issn = "0022-4065",
publisher = "American Society for Quality",
number = "2",

}

TY - JOUR

T1 - Interaction models as alternatives to low-order polynomials

AU - Cornell, John A.

AU - Montgomery, Douglas

PY - 1996/4

Y1 - 1996/4

N2 - One of the most popular classes of models that people fit empirically to data is the class of polynomials. One reason for this is, over limited-sized regions of interest, lower-degree polynomials (specifically, degrees 1, 2, and at most 3) have stood the test of time by proving their versatility when it comes to fitting a wide variety of different surface shapes. However, when faced with modeling a surface over an experimental region whose boundaries extend beyond some localized neighborhood or limited-sized region of interest, a polynomial of degree 2, or even of degree 3, may not be adequate. For this situation we propose fitting an interaction model which is a reduced form of a higher-degree polynomial. Several examples of actual experiments are presented to illustrate the improvement in fit by an interaction model over that of a standard polynomial, even for response surfaces with uncomplicated shapes.

AB - One of the most popular classes of models that people fit empirically to data is the class of polynomials. One reason for this is, over limited-sized regions of interest, lower-degree polynomials (specifically, degrees 1, 2, and at most 3) have stood the test of time by proving their versatility when it comes to fitting a wide variety of different surface shapes. However, when faced with modeling a surface over an experimental region whose boundaries extend beyond some localized neighborhood or limited-sized region of interest, a polynomial of degree 2, or even of degree 3, may not be adequate. For this situation we propose fitting an interaction model which is a reduced form of a higher-degree polynomial. Several examples of actual experiments are presented to illustrate the improvement in fit by an interaction model over that of a standard polynomial, even for response surfaces with uncomplicated shapes.

KW - Factorial Design

KW - Interactions

KW - Lack of Fit

KW - Misspecified Model

KW - Polynomial Model

KW - Response Surface Methodology

UR - http://www.scopus.com/inward/record.url?scp=0030129138&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030129138&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0030129138

VL - 28

SP - 163

EP - 176

JO - Journal of Quality Technology

JF - Journal of Quality Technology

SN - 0022-4065

IS - 2

ER -