Abstract

A monitoring scheme for detecting a mean shift in a multistage manufacturing process for a gamma distributed response and/or a mixture of normally and non-normally distributed variables (and gamma distributed responses) is presented. The procedure is based on a deviance residual obtained from a generalized linear model (GLM). The deviance residual is shown to be a likelihood ratio statistic for detecting a mean shift in many cases for distributions in the exponential family. The advantages over the use of a control chart based on individual observations and the T2 chart based on U statistics are demonstrated by a simulation study. The possibility of modelling the process variation for multistage processes based on a GLM is also discussed.

Original languageEnglish (US)
Pages (from-to)5547-5570
Number of pages24
JournalInternational Journal of Production Research
Volume45
Issue number23
DOIs
StatePublished - Dec 2007

Fingerprint

Process monitoring
Statistics
Monitoring
Mean shift
Deviance
Generalized linear model
Control charts

Keywords

  • Cascade process
  • Gamma responses
  • Generalized linear model
  • Model based control chart
  • Multistage process

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering
  • Management Science and Operations Research

Cite this

Process monitoring for mean shifts for multiple stage processes. / Jearkpaporn, D.; Borror, C. M.; Runger, George; Montgomery, Douglas.

In: International Journal of Production Research, Vol. 45, No. 23, 12.2007, p. 5547-5570.

Research output: Contribution to journalArticle

@article{bd3f71e872c542998f4a7e0a1826ea69,
title = "Process monitoring for mean shifts for multiple stage processes",
abstract = "A monitoring scheme for detecting a mean shift in a multistage manufacturing process for a gamma distributed response and/or a mixture of normally and non-normally distributed variables (and gamma distributed responses) is presented. The procedure is based on a deviance residual obtained from a generalized linear model (GLM). The deviance residual is shown to be a likelihood ratio statistic for detecting a mean shift in many cases for distributions in the exponential family. The advantages over the use of a control chart based on individual observations and the T2 chart based on U statistics are demonstrated by a simulation study. The possibility of modelling the process variation for multistage processes based on a GLM is also discussed.",
keywords = "Cascade process, Gamma responses, Generalized linear model, Model based control chart, Multistage process",
author = "D. Jearkpaporn and Borror, {C. M.} and George Runger and Douglas Montgomery",
year = "2007",
month = "12",
doi = "10.1080/00207540701325371",
language = "English (US)",
volume = "45",
pages = "5547--5570",
journal = "International Journal of Production Research",
issn = "0020-7543",
publisher = "Taylor and Francis Ltd.",
number = "23",

}

TY - JOUR

T1 - Process monitoring for mean shifts for multiple stage processes

AU - Jearkpaporn, D.

AU - Borror, C. M.

AU - Runger, George

AU - Montgomery, Douglas

PY - 2007/12

Y1 - 2007/12

N2 - A monitoring scheme for detecting a mean shift in a multistage manufacturing process for a gamma distributed response and/or a mixture of normally and non-normally distributed variables (and gamma distributed responses) is presented. The procedure is based on a deviance residual obtained from a generalized linear model (GLM). The deviance residual is shown to be a likelihood ratio statistic for detecting a mean shift in many cases for distributions in the exponential family. The advantages over the use of a control chart based on individual observations and the T2 chart based on U statistics are demonstrated by a simulation study. The possibility of modelling the process variation for multistage processes based on a GLM is also discussed.

AB - A monitoring scheme for detecting a mean shift in a multistage manufacturing process for a gamma distributed response and/or a mixture of normally and non-normally distributed variables (and gamma distributed responses) is presented. The procedure is based on a deviance residual obtained from a generalized linear model (GLM). The deviance residual is shown to be a likelihood ratio statistic for detecting a mean shift in many cases for distributions in the exponential family. The advantages over the use of a control chart based on individual observations and the T2 chart based on U statistics are demonstrated by a simulation study. The possibility of modelling the process variation for multistage processes based on a GLM is also discussed.

KW - Cascade process

KW - Gamma responses

KW - Generalized linear model

KW - Model based control chart

KW - Multistage process

UR - http://www.scopus.com/inward/record.url?scp=35348860311&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35348860311&partnerID=8YFLogxK

U2 - 10.1080/00207540701325371

DO - 10.1080/00207540701325371

M3 - Article

AN - SCOPUS:35348860311

VL - 45

SP - 5547

EP - 5570

JO - International Journal of Production Research

JF - International Journal of Production Research

SN - 0020-7543

IS - 23

ER -