On the Performance of Phase‐I Bivariate Dispersion Charts to Non‐Normality

A phase-I study is generally used when population parameters are unknown. The performance of any phase-II chart depends on the preciseness of the control limits obtained from the phase-I analysis. The performance of phase-I bivariate dispersion charts has mainly been investigated for bivariate normal distribution. However, this assumption is seldom fulfilled in reality. The current work develops and studies the performance of phase-I |S| and |G| charts for monitoring the process dispersion of bivariate non-normal distributions. The necessary control charting constants are determined for the bivariate non-normal distributions at nominal false alarm probability (FAP0). The performance of these charts is evaluated and compared in a situation when samples are generated by bivariate logistic, bivariate Laplace, bivariate exponential, or bivariate t5 distribution. The analysis shows that the proper consideration to underlying bivariate distribution in the construction of phase-I bivariate dispersion charts is very important to give a real picture of in or out of control process status. Copyright © 2016 John Wiley & Sons, Ltd.

[1]  Subha Chakraborti,et al.  Improved Phase I Control Charts for Monitoring Times Between Events , 2015, Qual. Reliab. Eng. Int..

[2]  Mi Lim Lee,et al.  Robust distribution-free multivariate CUSUM charts for spatiotemporal biosurveillance in the presence of spatial correlation , 2015 .

[3]  Douglas M. Hawkins,et al.  Combined Charts for Mean and Variance Information , 2009 .

[4]  N José Alberto Vargas,et al.  Comparison of Multivariate Control Charts for Process Dispersion , 2007 .

[5]  Zhonghua Li,et al.  A multivariate control chart for simultaneously monitoring process mean and variability , 2010, Comput. Stat. Data Anal..

[6]  M. A. Graham,et al.  Phase I Statistical Process Control Charts: An Overview and Some Results , 2008 .

[7]  Muhammad Riaz,et al.  Design and Analysis of Control Charts for Standard Deviation with Estimated Parameters , 2011 .

[8]  Zachary G. Stoumbos,et al.  Robustness to Non-Normality of the Multivariate EWMA Control Chart , 2002 .

[9]  Ipek Deveci Kocakoç,et al.  A Multivariate Change Point Detection Procedure for Monitoring Mean and Covariance Simultaneously , 2013, Commun. Stat. Simul. Comput..

[10]  Saddam Akber Abbasi,et al.  On the Performance of Phase I Dispersion Control Charts for Process Monitoring , 2015, Qual. Reliab. Eng. Int..

[11]  Longcheen Huwang,et al.  New EWMA control charts for monitoring process dispersion , 2010, Comput. Stat. Data Anal..

[12]  Stelios Psarakis,et al.  Multivariate statistical process control charts: an overview , 2007, Qual. Reliab. Eng. Int..

[13]  Marion R. Reynolds,et al.  Multivariate Monitoring of the Process Mean and Variability Using Combinations of Shewhart and MEWMA Control Charts , 2010 .

[14]  Charles W. Champ,et al.  A Distribution-Free Phase I Control Chart for Subgroup Scale , 2010 .

[15]  Arthur B. Yeh,et al.  Multivariate Control Charts for Monitoring Covariance Matrix: A Review , 2006 .

[16]  Muhammad Riaz,et al.  An Alternative to the Bivariate Control Chart for Process Dispersion , 2008 .

[17]  Arthur B. Yeh,et al.  A Nonparametric Phase I Control Chart for Individual Observations Based on Empirical Likelihood Ratio , 2015, Qual. Reliab. Eng. Int..

[18]  Subha Chakraborti,et al.  Shewhart-type control charts for variation in phase I data analysis , 2010, Comput. Stat. Data Anal..

[19]  Ronald J. M. M. Does,et al.  A Robust Phase I Exponentially Weighted Moving Average Chart for Dispersion , 2015, Qual. Reliab. Eng. Int..

[20]  Aamir Saghir,et al.  The bivariate dispersion control charts for non-normal processes , 2015 .