Cover Image

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
http://eprints.utm.my/id/eprint/54897/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.54897
record_format eprints
spelling my.utm.548972017-04-26T04:27:36Z http://eprints.utm.my/id/eprint/54897/ Enhanced exponentially weighted moving average (EWMA) control chart performance with autocorrelation 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 NonPeerReviewed application/pdf en http://eprints.utm.my/id/eprint/54897/1/AbbasUmarFaroukPFS2015.pdf Farouk, Abbas Umar (2015) Enhanced exponentially weighted moving average (EWMA) control chart performance with autocorrelation. PhD thesis, Universiti Teknologi Malaysia, Faculty of Science.
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
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
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
publishDate 2015
url http://eprints.utm.my/id/eprint/54897/1/AbbasUmarFaroukPFS2015.pdf
http://eprints.utm.my/id/eprint/54897/
_version_ 1643653638670778368
score 13.211869

Similar Items