ALTopt: An R package for optimal experimental design of accelerated life testing

Kangwon Seo, Rong Pan

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

The R package ALTopt has been developed with the aim of creating and evaluating optimal experimental designs of censored accelerated life tests (ALTs). This package takes the generalized linear model approach to ALT planning, because this approach can easily handle censoring plans and derive information matrices for evaluating designs. Three types of optimality criteria are considered: D-optimality for model parameter estimation, U-optimality for reliability prediction at a single use condition, and I-optimality for reliability prediction over a region of use conditions. The Weibull distribution is assumed for failure time data and more than one stress factor can be specified in the package. Several graphical evaluation tools are also provided for the comparison of different ALT test plans.

Original languageEnglish (US)
Pages (from-to)177-188
Number of pages12
JournalR Journal
Volume7
Issue number2
StatePublished - 2015

Fingerprint

Accelerated Life Testing
Optimal Experimental Design
Accelerated Life Test
Design of experiments
Weibull distribution
Optimality
Testing
Parameter estimation
D-optimality
Failure Time Data
Information Matrix
Prediction
Optimality Criteria
Weibull Distribution
Generalized Linear Model
Censoring
Planning
Parameter Estimation
Evaluation
Experimental design

ASJC Scopus subject areas

  • Statistics and Probability
  • Numerical Analysis
  • Statistics, Probability and Uncertainty

Cite this

ALTopt : An R package for optimal experimental design of accelerated life testing. / Seo, Kangwon; Pan, Rong.

In: R Journal, Vol. 7, No. 2, 2015, p. 177-188.

Research output: Contribution to journalArticle

@article{6fe030dbacbf4fdaa33dbf74cda29385,
title = "ALTopt: An R package for optimal experimental design of accelerated life testing",
abstract = "The R package ALTopt has been developed with the aim of creating and evaluating optimal experimental designs of censored accelerated life tests (ALTs). This package takes the generalized linear model approach to ALT planning, because this approach can easily handle censoring plans and derive information matrices for evaluating designs. Three types of optimality criteria are considered: D-optimality for model parameter estimation, U-optimality for reliability prediction at a single use condition, and I-optimality for reliability prediction over a region of use conditions. The Weibull distribution is assumed for failure time data and more than one stress factor can be specified in the package. Several graphical evaluation tools are also provided for the comparison of different ALT test plans.",
author = "Kangwon Seo and Rong Pan",
year = "2015",
language = "English (US)",
volume = "7",
pages = "177--188",
journal = "R Journal",
issn = "2073-4859",
publisher = "R Foundation for Statistical Computing",
number = "2",

}

TY - JOUR

T1 - ALTopt

T2 - An R package for optimal experimental design of accelerated life testing

AU - Seo, Kangwon

AU - Pan, Rong

PY - 2015

Y1 - 2015

N2 - The R package ALTopt has been developed with the aim of creating and evaluating optimal experimental designs of censored accelerated life tests (ALTs). This package takes the generalized linear model approach to ALT planning, because this approach can easily handle censoring plans and derive information matrices for evaluating designs. Three types of optimality criteria are considered: D-optimality for model parameter estimation, U-optimality for reliability prediction at a single use condition, and I-optimality for reliability prediction over a region of use conditions. The Weibull distribution is assumed for failure time data and more than one stress factor can be specified in the package. Several graphical evaluation tools are also provided for the comparison of different ALT test plans.

AB - The R package ALTopt has been developed with the aim of creating and evaluating optimal experimental designs of censored accelerated life tests (ALTs). This package takes the generalized linear model approach to ALT planning, because this approach can easily handle censoring plans and derive information matrices for evaluating designs. Three types of optimality criteria are considered: D-optimality for model parameter estimation, U-optimality for reliability prediction at a single use condition, and I-optimality for reliability prediction over a region of use conditions. The Weibull distribution is assumed for failure time data and more than one stress factor can be specified in the package. Several graphical evaluation tools are also provided for the comparison of different ALT test plans.

UR - http://www.scopus.com/inward/record.url?scp=84954157888&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84954157888&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84954157888

VL - 7

SP - 177

EP - 188

JO - R Journal

JF - R Journal

SN - 2073-4859

IS - 2

ER -