A Robust Phase I Exponentially Weighted Moving Average Chart for Dispersion

A Robust Phase I Exponentially Weighted Moving Average Chart for Dispersion

0.00 Avg rating0 Votes
Article ID: iaor201528916
Volume: 31
Issue: 6
Start Page Number: 989
End Page Number: 999
Publication Date: Oct 2015
Journal: Quality and Reliability Engineering International
Authors: , ,
Keywords: control charts, estimation, moving averages
Abstract:

A Phase I estimator of the dispersion should be efficient under in‐control data and robust against contaminations. Most estimation methods proposed in the literature are either efficient or robust against either sustained shifts or scattered disturbances. In this article, we propose a new estimation method of the dispersion parameter, based on exponentially weighted moving average charting, which is efficient and robust to both types of unacceptable observations in Phase I. We compare the 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. We also study the effect of the robust estimator from Phase I on the Phase II exponentially weighted moving average control chart performance.

Reviews

Required fields are marked *. Your email address will not be published.