Design of an extended nonparametric EWMA sign chart

Selecting a suitable control chart is essential to effectively mon itoring process shifts. In particularly, a nonparametric control chart is recommended over a traditional control chart when the quality characteristics of a process are unknown. In this study, we propose a new algorithm that extended the nonparametric exponentially weighted moving average (EWMA) sign chart to a double EWMA (DEWMA) sign chart to improve the detection ability in small process shifts. Simulation studies show that the nonparametric DEWMA sign chart performs better than the EWMA sign chart in detecting small process shifts, but that they perform similarly when detecting large shifts. A real-life example of service times from a service system of a bank branch in Taiwan is used to illustrate the proposed novel nonparametric DEWMA sign chart. © 2015 International Journal of Industrial Engineering.