Mixed Tukey-Double Moving Average for Monitoring of Process Mean

Abstract

A double moving average (DMA) control chart is used to detect smaller shifts in the process parameters. The DMA chart depends on the normality assumption for a better detection ability. This article is a similar effort to design an improvement the charting structure in the form of a mixed Tukey-Double moving average control chart (namely Tukey-DMA), specially designed for symmetric and asymmetric processes. The comparative analysis has revealed that the proposed scheme is an effective competitor to the existing counterparts, including Tukey, DMA, and Tukey-MA. The performance of the proposed and the competing charts are measured using Average run length (ARL). Moreover, the proposed design presents some of the aforementioned charts as special cases. For practical considerations, we have implemented the proposed and existing charts to two real-life data sets, one related to Nile river flow and the other one concerning British coal mining disaster.