Mixed CUSUM-EWMA chart for monitoring process dispersion

Every industrial process has to encounter two types of variation in product characteristic(s) that can be classified as common and special cause variations. These variations can exist in any parameters (like location, dispersion, shape, etc.) of the distribution of process characteristic. To handle the special cause variations, statistical tools are generally used to handle these special cause variations; statistical control chart is one of them. The most famous control charts are Shewhart, exponentially weighted moving average and cumulative sum charts, and their substantial modifications are available in the literature. In this article, we have proposed a new control chart named as mixed CUSUM-EWMA (called MCE) control chart for the efficient monitoring of process dispersion. The proposed MCE chart is compared with other existing control charts and some of their modifications. Average run length, extra quadratic loss, relative average run length, and performance comparison index are the measures that are used to judge the performance of charts. For practical considerations, an illustrative example with real data is also provided.