A Robust Phase I Ewma Chart for Dispersion

• Activity Number: 446
• Type: Topic Contributed
• Date/Time: Wednesday, August 6, 2014 : 8:30 AM to 10:20 AM
• Sponsor: Quality and Productivity Section
• Author(s): Ronald Does*+ and Inez Zwetsloot and Marit Schoonhoven
• Companies: University of Amsterdam and University of Amsterdam and University of Amsterdam
• Keywords: Statistical Process Control ; Monitoring ; Contaminations ; Outliers ; Changepoint

Abstract

Current design schemes for control charts with estimated parameters are often based on the assumption of in-control Phase I data. However, the Phase I data set can contain unusual observations, which are problematic as they can influence the parameter estimates, resulting in Phase II control charts with less ability to detect changes in process characteristic. In this talk, we consider the problem of estimating the process dispersion when the Phase I data may or may not contain contaminated observations. Considerable work has been published on alternative estimators, these are either efficient or robust against either sustained shifts or scattered disturbances. We propose a new estimation method of the dispersion, based on EWMA control charting, which provides reliable estimates irrespective of the type of disturbances present in Phase I. We conduct a simulation study to compare this method with various existing estimation methods and show that the proposed method has the best overall performance if it is unknown what type of contaminations are present in Phase I.