Abstract—This paper aims to study the robustness of Double Exponentially Weighted Moving Average (DEWMA) in order to detect a change in parameter when process are underlying skew distributions. In general, an Average Run Length (ARL) is used as a common measurement to compare the performance of control chart in term of quick detection. The performance of GWMA chart are compared with Exponentially Weighted Moving Average (EWMA) and Generally Weighted Moving Average Control Chart (GWMA) charts which the former outperforms and give a minimal ARL1 for all magnitudes of shift.

Index Terms—Performance, monitoring, skewness, control chart.

Saowanit Sukparungsee is with Department of Applied Statistics, Faculty of Applied Science, King Mongkut’s University of Technology North Bangkok, Bangkok, Thailand (email: saowanit.s@sci.kmutnb.ac.th).

Cite: Saowanit Sukparungsee, "Robustness of Memory-Type Charts to Skew Processes," International Journal of Applied Physics and Mathematics vol. 6, no. 4, pp. 165-171, 2016.