Sensitivity analysis of optimal designs for accelerated life testing

Eric M. Monroe, Rong Pan, Christine M. Anderson-Cook, Douglas Montgomery, Connie M. Borror

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

In experimental testing, it is desirable to select combinations of input factors that yield optimal results given an objective specified by a practitioner. Often this objective involves minimizing the uncertainty in a parameter or prediction estimate. To determine the experimental design to achieve such an objective, it is necessary to understand the relationship between the testing variables and the response. Alphabetic optimal designs are commonly used in such applications based largely on the ease of their construction with advanced statistical software. However, many publications cite concerns with the overall robustness of such designs to small departures in parameter estimates. This paper examines the issue of model parameter sensitivity to the selection of an accelerated life test based on the UC-optimality criterion, minimizing of the prediction variance at the usage condition, using a generalized linear model framework. We will examine the trade-off implications of choice of experimental design, sample size, and censoring.

Original languageEnglish (US)
Pages (from-to)121-135
Number of pages15
JournalJournal of Quality Technology
Volume42
Issue number2
StatePublished - Apr 2010

Fingerprint

Design of experiments
Sensitivity analysis
Testing
Optimal design
Experimental design
Prediction
Uncertainty
Factors
Optimality
Censoring
Sample size
Trade-offs
Robustness
Generalized linear model
Software

Keywords

  • Design of experiments
  • Reliability testing
  • Robustness
  • UC-optimality
  • Use condition

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering
  • Safety, Risk, Reliability and Quality
  • Strategy and Management
  • Management Science and Operations Research

Cite this

Sensitivity analysis of optimal designs for accelerated life testing. / Monroe, Eric M.; Pan, Rong; Anderson-Cook, Christine M.; Montgomery, Douglas; Borror, Connie M.

In: Journal of Quality Technology, Vol. 42, No. 2, 04.2010, p. 121-135.

Research output: Contribution to journalArticle

Monroe, EM, Pan, R, Anderson-Cook, CM, Montgomery, D & Borror, CM 2010, 'Sensitivity analysis of optimal designs for accelerated life testing', Journal of Quality Technology, vol. 42, no. 2, pp. 121-135.
Monroe, Eric M. ; Pan, Rong ; Anderson-Cook, Christine M. ; Montgomery, Douglas ; Borror, Connie M. / Sensitivity analysis of optimal designs for accelerated life testing. In: Journal of Quality Technology. 2010 ; Vol. 42, No. 2. pp. 121-135.
@article{78e588e22a7944769cb747ef17ae393e,
title = "Sensitivity analysis of optimal designs for accelerated life testing",
abstract = "In experimental testing, it is desirable to select combinations of input factors that yield optimal results given an objective specified by a practitioner. Often this objective involves minimizing the uncertainty in a parameter or prediction estimate. To determine the experimental design to achieve such an objective, it is necessary to understand the relationship between the testing variables and the response. Alphabetic optimal designs are commonly used in such applications based largely on the ease of their construction with advanced statistical software. However, many publications cite concerns with the overall robustness of such designs to small departures in parameter estimates. This paper examines the issue of model parameter sensitivity to the selection of an accelerated life test based on the UC-optimality criterion, minimizing of the prediction variance at the usage condition, using a generalized linear model framework. We will examine the trade-off implications of choice of experimental design, sample size, and censoring.",
keywords = "Design of experiments, Reliability testing, Robustness, UC-optimality, Use condition",
author = "Monroe, {Eric M.} and Rong Pan and Anderson-Cook, {Christine M.} and Douglas Montgomery and Borror, {Connie M.}",
year = "2010",
month = "4",
language = "English (US)",
volume = "42",
pages = "121--135",
journal = "Journal of Quality Technology",
issn = "0022-4065",
publisher = "American Society for Quality",
number = "2",

}

TY - JOUR

T1 - Sensitivity analysis of optimal designs for accelerated life testing

AU - Monroe, Eric M.

AU - Pan, Rong

AU - Anderson-Cook, Christine M.

AU - Montgomery, Douglas

AU - Borror, Connie M.

PY - 2010/4

Y1 - 2010/4

N2 - In experimental testing, it is desirable to select combinations of input factors that yield optimal results given an objective specified by a practitioner. Often this objective involves minimizing the uncertainty in a parameter or prediction estimate. To determine the experimental design to achieve such an objective, it is necessary to understand the relationship between the testing variables and the response. Alphabetic optimal designs are commonly used in such applications based largely on the ease of their construction with advanced statistical software. However, many publications cite concerns with the overall robustness of such designs to small departures in parameter estimates. This paper examines the issue of model parameter sensitivity to the selection of an accelerated life test based on the UC-optimality criterion, minimizing of the prediction variance at the usage condition, using a generalized linear model framework. We will examine the trade-off implications of choice of experimental design, sample size, and censoring.

AB - In experimental testing, it is desirable to select combinations of input factors that yield optimal results given an objective specified by a practitioner. Often this objective involves minimizing the uncertainty in a parameter or prediction estimate. To determine the experimental design to achieve such an objective, it is necessary to understand the relationship between the testing variables and the response. Alphabetic optimal designs are commonly used in such applications based largely on the ease of their construction with advanced statistical software. However, many publications cite concerns with the overall robustness of such designs to small departures in parameter estimates. This paper examines the issue of model parameter sensitivity to the selection of an accelerated life test based on the UC-optimality criterion, minimizing of the prediction variance at the usage condition, using a generalized linear model framework. We will examine the trade-off implications of choice of experimental design, sample size, and censoring.

KW - Design of experiments

KW - Reliability testing

KW - Robustness

KW - UC-optimality

KW - Use condition

UR - http://www.scopus.com/inward/record.url?scp=79951873732&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79951873732&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:79951873732

VL - 42

SP - 121

EP - 135

JO - Journal of Quality Technology

JF - Journal of Quality Technology

SN - 0022-4065

IS - 2

ER -