A Nonparametric Change Point Model for Multivariate Phase II Statistical Process Control

• Activity Number: 475
• Type: Contributed
• Date/Time: Wednesday, August 4, 2010 : 8:30 AM to 10:20 AM
• Sponsor: Section on Quality and Productivity
• Author(s): Mark David Holland*+ and Douglas Hawkins
• Companies: University of Minnesota and University of Minnesota
• Keywords: change point model ; statistical process control ; multivariate rank

Abstract

Phase II statistical process control (SPC) procedures are designed to detect a change in distribution when a possibly never-ending stream of observations is collected. Extensive study has been conducted to detect shifts in location (e.g. mean or median) when univariate observations are collected. Many techniques have also been proposed to detect a shift in location vector for multivariate observations. These procedures require the user to make assumptions about the distribution of the process readings, to assume that process parameters are known, or to collect a large training sample before monitoring the ongoing process for a change in distribution. We propose a multivariate rank based procedure using recursive residuals that does not require the user to make strong assumptions, or to collect a large training sample before monitoring the process for a shift in location vector.