Author, Subjects, Keywords

Cited Author

 
 
   » By Author or Editor
 » Browse Author by Alphabet
 » By Journal
 » By Subjects
 » Malaysian Journals
 » By Type
 » By Year
 » By Latest Additions
 
 
   » By Author
 » Top 20 Authors
 » Top 20 Article
 » Top Journal Cited
 » Top Article Cited
 » Journal Citation Statistics
 » Usage Since Sept 2007


 
 
 

Login | Create Account

A Comparison of Performances of Three Types of Control Charts for Skewed Distributions

Khoo, Michael B.C., and Mazidah Kassim, (2008) A Comparison of Performances of Three Types of Control Charts for Skewed Distributions. Matematika, 24 (2). pp. 169-185. ISSN 01278274

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
267Kb

Official URL: http://www.fs.utm.my/matematika/images/stories/matematika/20082427.pdf

Affiliations

Universiti Sains Malaysia, School of Mathematical Studies
Universiti Sains Malaysia, School of Mathematical Studies

Abstract

This paper compares three different types of control charting methods used in the monitoring of a process mean from a skewed distribution. The skewed distributions considered are the Weibull, lognormal and gamma distributions while the control charts for skewed distributions studied are the weighted variance ¯X chart `WV − ¯X chart´ , weighted standard deviation ¯X chart `WSD − ¯X chart´ and skewness correction ¯X chart (SC − ¯X chart). These charts will be evaluated based on their in-control average run length (ARL0) performances. ARL is defined as the average number of sample points that must be plotted on a control chart before the first point plots beyond the control limits. Since these charts are designed based on the three standard deviation width, ARL0 _ 370 is considered when the underlying distribution of a process is normal. A good chart has a large ARL0 value when the process follows a skewed distribution. A performance comparison based on a simulation study using the Statistical Analysis System (SAS) version 9 program shows that the SC − ¯X and WSD − ¯X charts have better ARL0 performances than the WV − ¯X chart. The SC − ¯X and WSD − ¯X charts have about the same ARL0 performances.

Item Type:Journal
Keywords:Control chart; skewed distribution; weighted variance (WV); weighted; standard deviation (WSD); skewness correction (SC); average run length (ARL); process mean.
Subjects:Q Science, Computer Science
L Education
ID Code:5394

[1] D.C. Montgomery, Introduction to Statistical Quality Control, 5th. ed., John Wiley & Sons, Inc., New York, 2005.

[2] D.S. Bai dan I.S. Choi, ¯X and R Control Charts for Skewed Populations, Journal of Quality Technology, 27(1995), 120 – 131.

[3] I.W. Burr, The Effect of Non-normality on Constants for ¯X and R Charts, Industrial Quality Control, 24(1967), 563 – 569.

[4] E.G. Schilling dan P.R. Nelson, The Effect of Non-normality on the Control Limits of ¯X Charts, Journal of Quality Technology, 8(1976), 183 – 188.

[5] N. Balakrishnan dan S. Kocherlakota, Effects of Non-normality on ¯X Charts : Single Assignable Cause Model, Sankya B, 48(1986), 439 – 444.

[6] L.K. Chan, K.P. Hapuarachchi dan B.D. Macpherson, Robustness of ¯X and R Charts, IEEE Transactions on Reliability, 37(1988), 117 – 123.

[7] Y.S. Chang dan D.S. Bai, Control Charts for Positively-Skewed Populations with Weighted Standard Deviations, Quality and Reliability Engineering International, 17(2001), 397 – 406.

[8] L.K. Chan dan H.J. Cui, Skewness Correction ¯X and R Charts for Skewed Distributions, Naval Research Logistics, 50(2003), 555 – 573.

[9] Y.S. Chang dan D.S. Bai, A Multivariate T2Control Chart for Skewed Populations Using Weighted Standard Deviations, Quality and Reliability Engineering International, 20(2004), 31 – 46.

[10] Y.S. Chang, Multivariate CUSUM and EWMA Control Charts for Skewed Populations Using Weighted Standard Deviations, Communications in Statistics – Simulation and Computation, 36(2007), 921 – 936.

Repository Staff Only: item control page
 
 
 
 
 
 
© Copyright 2007 MyAIS Faculty of Computer Science and Information Technology, University of Malaya – All Rights Reserved. Malaysian Abstracting and Indexing System is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.