A Robust Dispersion Control Chart based on Modified Trimmed Standard Deviation

Abstract

Control Chart is a widely used on-line process control techniques to control variability. This paper focuses on variability due to dispersion of a quality characteristic. Classical methods of estimating parameters of the distribu- tion of quality characteristic may be affected by the presence of outliers. In order to overcome such situation, robust estimators, which are less affected by the extreme values or small departures from the model assumptions, are introduced in industrial application. This article introduced a modification to trimmed standard deviation to increase its efficiency, and is used in con- trolling process dispersion. Authors constructed a phase-I control chart de- rived from standard deviation of trimmed mean, which is robust. Simulation study is conducted to assess its performance at phase-II. This robust control chart is compared with s-chart in terms of its efficiency to detect outliers or assignable causes of variation as well as its Average Run Length.