Logo image
Back
EWMA Control Charts for the Smallest and Largest Observations
Journal article   Peer reviewed

EWMA Control Charts for the Smallest and Largest Observations

Raid W. Amin, Hans Wolff, Werner Besenfelder and Robert Baxley
Journal of quality technology, Vol.31(2), pp.189-206
04/01/1999
DOI: https://doi.org/10.1080/00224065.1999.11979914
Web of Science ID: WOS:000080342300005

Metrics

13 Record Views
48 Times Cited - Web of Science

Abstract

In this article, we propose an exponentially weighted moving average (EWMA) control chart based on the smallest (Min) and largest observations (Max) in each sample, which we call the MaxMin EWMA control chart. When there is a change in the process, the proposed control chart (and its modification) shows which parameters have increased or decreased. Also, the MaxMin EWMA may be viewed as smoothed tolerance limits, and it offers useful graphical guidance for monitoring processes and for trouble shooting. We give a design procedure and develop a two-dimensional Markov chain to approximate the average run length (ARL) for the proposed control chart. Our numerical results show that the MaxMin EWMA chart has good ARL properties for simultaneous changes in the mean and standard deviation. We provide a comparison with the combined use of X̄ and ℓn(S 2 ) EWMA charts. We present an application with 100 multi-stream processes in which the MaxMin EWMA chart has already been successfully field tested and subsequently implemented.

Details

Logo image