Enhanced exponentially weighted moving average (EWMA) control chart performance with autocorrelation

This research introduces an enhanced exponentially weighted moving average (EWMA) control chart which is effective in detecting small and unnoticed shifts in monitoring process mean for autocorrelated data. The control chart is based on extension or modification of EWMA control chart statistic. The...

Full description

Saved in:

Bibliographic Details
Main Author:	Farouk, Abbas Umar
Format:	Thesis
Language:	English
Published:	2015
Subjects:	QA Mathematics
Online Access:	http://eprints.utm.my/id/eprint/54897/1/AbbasUmarFaroukPFS2015.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-utm-ep.54897
record_format	uketd_dc
spelling	my-utm-ep.548972017-04-26T04:27:36Z Enhanced exponentially weighted moving average (EWMA) control chart performance with autocorrelation 2015-04 Farouk, Abbas Umar QA Mathematics This research introduces an enhanced exponentially weighted moving average (EWMA) control chart which is effective in detecting small and unnoticed shifts in monitoring process mean for autocorrelated data. The control chart is based on extension or modification of EWMA control chart statistic. The proposed control chart is named the new EWMA (NEWMA) and is applied to simulated autocorrelated data for different autocorrelation levels (low, moderate and large) to study the performance of the chart. The run rules schemes were introduced to enhance the performance of the NEWMA chart namely; three out of three and three out of four schemes and three out of four is the best among the schemes. The NEWMA chart performs for observations that are autocorrelated. The NEWMA control chart has been tested on 100,000 simulations and it is found that it is quick in detecting process shift and able to identify the out of control points as it occurs. The performance of the technique has been evaluated using the average run length (ARL) and compared with modified exponentially weighted moving average (MEWMA) and classical exponentially weighted moving average (CEWMA) control charts and found that the NEWMA chart is faster in detecting shift. The NEWMA chart was applied to the KLSE Share index data, water quality data and Malaysian labour force data which are autocorrelated in nature and found to be effective in detecting the shifts. 2015-04 Thesis http://eprints.utm.my/id/eprint/54897/ http://eprints.utm.my/id/eprint/54897/1/AbbasUmarFaroukPFS2015.pdf application/pdf en public phd doctoral Universiti Teknologi Malaysia, Faculty of Science Faculty of Science
institution	Universiti Teknologi Malaysia
collection	UTM Institutional Repository
language	English
topic	QA Mathematics
spellingShingle	QA Mathematics Farouk, Abbas Umar Enhanced exponentially weighted moving average (EWMA) control chart performance with autocorrelation
description	This research introduces an enhanced exponentially weighted moving average (EWMA) control chart which is effective in detecting small and unnoticed shifts in monitoring process mean for autocorrelated data. The control chart is based on extension or modification of EWMA control chart statistic. The proposed control chart is named the new EWMA (NEWMA) and is applied to simulated autocorrelated data for different autocorrelation levels (low, moderate and large) to study the performance of the chart. The run rules schemes were introduced to enhance the performance of the NEWMA chart namely; three out of three and three out of four schemes and three out of four is the best among the schemes. The NEWMA chart performs for observations that are autocorrelated. The NEWMA control chart has been tested on 100,000 simulations and it is found that it is quick in detecting process shift and able to identify the out of control points as it occurs. The performance of the technique has been evaluated using the average run length (ARL) and compared with modified exponentially weighted moving average (MEWMA) and classical exponentially weighted moving average (CEWMA) control charts and found that the NEWMA chart is faster in detecting shift. The NEWMA chart was applied to the KLSE Share index data, water quality data and Malaysian labour force data which are autocorrelated in nature and found to be effective in detecting the shifts.
format	Thesis
qualification_name	Doctor of Philosophy (PhD.)
qualification_level	Doctorate
author	Farouk, Abbas Umar
author_facet	Farouk, Abbas Umar
author_sort	Farouk, Abbas Umar
title	Enhanced exponentially weighted moving average (EWMA) control chart performance with autocorrelation
title_short	Enhanced exponentially weighted moving average (EWMA) control chart performance with autocorrelation
title_full	Enhanced exponentially weighted moving average (EWMA) control chart performance with autocorrelation
title_fullStr	Enhanced exponentially weighted moving average (EWMA) control chart performance with autocorrelation
title_full_unstemmed	Enhanced exponentially weighted moving average (EWMA) control chart performance with autocorrelation
title_sort	enhanced exponentially weighted moving average (ewma) control chart performance with autocorrelation
granting_institution	Universiti Teknologi Malaysia, Faculty of Science
granting_department	Faculty of Science
publishDate	2015
url	http://eprints.utm.my/id/eprint/54897/1/AbbasUmarFaroukPFS2015.pdf
_version_	1747817750371237888

Enhanced exponentially weighted moving average (EWMA) control chart performance with autocorrelation

Similar Items