A nonparametric control chart based on the empirical characteristic function

This paper proposes a nonparametric multivariate control chart in the context of rational sub-grouping. The proposed approach combines an EWMA scheme with a two-sample test based on the empirical characteristic function. The new procedure is able to detect changes across the entire distribution, rather than just shifts in location and scale. Numerical studies demonstrate the effectiveness of the proposed approach, which is further illustrated using a real data set from semiconductor manufacturing.