A Multistep, Cluster-Based Multivariate Chart for Retrospective Monitoring of Individuals

Abstract

The presence of several outliers in an individuals retrospective multivariate control chart distorts both the sample mean vector and covariance matrix, making the classical Hotelling's T² approach unreliable for outlier detection. To overcome the distortion or masking, we propose a computer-intensive multistep cluster-based method. Compared with classical and robust estimation procedures, simulation studies show that our method is usually better and sometimes much better at detecting randomly occurring outliers as well as outliers arising from shifts in the process location. Additional comparisons based on real data are given.

• Breakdown Point
• Cluster Analysis
• Kernel Estimation
• Mahalanobis Distance
• Moving Average and Medoid
• Outlier

Additional information

Notes on contributors

J. Marcus Jobe

Dr. Jobe is a Professor in the Decision Sciences and Management Information Systems Department, Miami University. His email address is [email protected].

Michael Pokojovy

Mr. Pokojovy is a Mathematics Research Fellow, Fachbereich Mathematik und Statistik, Universität Konstanz. His email address is [email protected].