A generalized likelihood ratio test for monitoring profile data

Research output: Contribution to conferencePaper

Abstract

Profile data emerges when the quality of a product or process is characterized by a functional relationship among (input and output) variables. In this paper, it is assumed that each profile has one response variable Y, one explanatory variable x, and the functional relationship between these two variables can be rather arbitrary. We propose a general method based on the Generalized Likelihood Ratio Test (GLRT) to perform Phase II monitoring of profile data. Unlike existing methods in profile monitoring area, the proposed method uses nonparametric regression to estimate the on-line profiles and thus does not require any functional form for the profiles. Both Shewhart-type and EWMA-type control charts are considered. The average run length (ARL) performance of the proposed method is studied by using a nonlinear profile dataset. It is shown that the proposed GLRT-based control chart can efficiently detect both location and dispersion shifts of the on-line profiles from the baseline profile. An upper control limit (UCL) corresponding to a desired in-control ARL value is constructed.

Original languageEnglish (US)
Pages309-325
Number of pages17
StatePublished - Jan 1 2016
Event12th International Workshop on Intelligent Statistical Quality Control, IWISQC 2016 - Hamburg, Germany
Duration: Aug 16 2016Aug 19 2016

Other

Other12th International Workshop on Intelligent Statistical Quality Control, IWISQC 2016
CountryGermany
CityHamburg
Period8/16/168/19/16

Fingerprint

Monitoring
Control charts

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Safety, Risk, Reliability and Quality

Cite this

Liu, Y., Zhu, J., & Lin, D. K. J. (2016). A generalized likelihood ratio test for monitoring profile data. 309-325. Paper presented at 12th International Workshop on Intelligent Statistical Quality Control, IWISQC 2016, Hamburg, Germany.
Liu, Yang ; Zhu, Junjia ; Lin, Dennis K.J. / A generalized likelihood ratio test for monitoring profile data. Paper presented at 12th International Workshop on Intelligent Statistical Quality Control, IWISQC 2016, Hamburg, Germany.17 p.
@conference{df79d335d4864212bb4c66bdded11167,
title = "A generalized likelihood ratio test for monitoring profile data",
abstract = "Profile data emerges when the quality of a product or process is characterized by a functional relationship among (input and output) variables. In this paper, it is assumed that each profile has one response variable Y, one explanatory variable x, and the functional relationship between these two variables can be rather arbitrary. We propose a general method based on the Generalized Likelihood Ratio Test (GLRT) to perform Phase II monitoring of profile data. Unlike existing methods in profile monitoring area, the proposed method uses nonparametric regression to estimate the on-line profiles and thus does not require any functional form for the profiles. Both Shewhart-type and EWMA-type control charts are considered. The average run length (ARL) performance of the proposed method is studied by using a nonlinear profile dataset. It is shown that the proposed GLRT-based control chart can efficiently detect both location and dispersion shifts of the on-line profiles from the baseline profile. An upper control limit (UCL) corresponding to a desired in-control ARL value is constructed.",
author = "Yang Liu and Junjia Zhu and Lin, {Dennis K.J.}",
year = "2016",
month = "1",
day = "1",
language = "English (US)",
pages = "309--325",
note = "12th International Workshop on Intelligent Statistical Quality Control, IWISQC 2016 ; Conference date: 16-08-2016 Through 19-08-2016",

}

Liu, Y, Zhu, J & Lin, DKJ 2016, 'A generalized likelihood ratio test for monitoring profile data' Paper presented at 12th International Workshop on Intelligent Statistical Quality Control, IWISQC 2016, Hamburg, Germany, 8/16/16 - 8/19/16, pp. 309-325.

A generalized likelihood ratio test for monitoring profile data. / Liu, Yang; Zhu, Junjia; Lin, Dennis K.J.

2016. 309-325 Paper presented at 12th International Workshop on Intelligent Statistical Quality Control, IWISQC 2016, Hamburg, Germany.

Research output: Contribution to conferencePaper

TY - CONF

T1 - A generalized likelihood ratio test for monitoring profile data

AU - Liu, Yang

AU - Zhu, Junjia

AU - Lin, Dennis K.J.

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Profile data emerges when the quality of a product or process is characterized by a functional relationship among (input and output) variables. In this paper, it is assumed that each profile has one response variable Y, one explanatory variable x, and the functional relationship between these two variables can be rather arbitrary. We propose a general method based on the Generalized Likelihood Ratio Test (GLRT) to perform Phase II monitoring of profile data. Unlike existing methods in profile monitoring area, the proposed method uses nonparametric regression to estimate the on-line profiles and thus does not require any functional form for the profiles. Both Shewhart-type and EWMA-type control charts are considered. The average run length (ARL) performance of the proposed method is studied by using a nonlinear profile dataset. It is shown that the proposed GLRT-based control chart can efficiently detect both location and dispersion shifts of the on-line profiles from the baseline profile. An upper control limit (UCL) corresponding to a desired in-control ARL value is constructed.

AB - Profile data emerges when the quality of a product or process is characterized by a functional relationship among (input and output) variables. In this paper, it is assumed that each profile has one response variable Y, one explanatory variable x, and the functional relationship between these two variables can be rather arbitrary. We propose a general method based on the Generalized Likelihood Ratio Test (GLRT) to perform Phase II monitoring of profile data. Unlike existing methods in profile monitoring area, the proposed method uses nonparametric regression to estimate the on-line profiles and thus does not require any functional form for the profiles. Both Shewhart-type and EWMA-type control charts are considered. The average run length (ARL) performance of the proposed method is studied by using a nonlinear profile dataset. It is shown that the proposed GLRT-based control chart can efficiently detect both location and dispersion shifts of the on-line profiles from the baseline profile. An upper control limit (UCL) corresponding to a desired in-control ARL value is constructed.

UR - http://www.scopus.com/inward/record.url?scp=85009875681&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009875681&partnerID=8YFLogxK

M3 - Paper

SP - 309

EP - 325

ER -

Liu Y, Zhu J, Lin DKJ. A generalized likelihood ratio test for monitoring profile data. 2016. Paper presented at 12th International Workshop on Intelligent Statistical Quality Control, IWISQC 2016, Hamburg, Germany.