Resumen de Nonparametric CUSUM and EWMA Control Charts for Detecting Mean Shifts

Su-Yi Li, Loon Ching Tang, Szu-Hui NG

• Two nonparametric analogs of the CUSUM and EWMA control charts based on the Wilcoxon rank-sum test are proposed for detecting process mean shifts. The charts perform well in detecting step mean shifts and better than competing parametric charts when the process output is nonnormal. The effect of the reference sample size and the subgroup size on the performance of the charts is also discussed.