Optimal Exponentially Weighted Moving Average Of T2 Chart

Abstract

We propose a chart for normal variables that uses a statistic that is a recursive form of Hotelling's T 2 statistic. The objective of this study is to improve the performance of the T 2 chart. To analyse the performance of this chart, we have developed a user-friendly program that finds the best parameters through Genetic Algorithms. This algorithm minimises the out-of-control ARL (Average Run Length) for a proposed shift in the mean vector under the restriction of a desired in-control ARL value. The proposed control chart shows better performance than the Hotelling T 2 chart.