International Journal of Statistics and Systems

The Shewhart S control chart is usually applied to monitor the process standard deviation of a quality characteristic. The control limits for this control chart are constructed based on the assumption that the underlying distribution of the quality characteristic is normal and no major contamination due to outliers. The sample standard deviation, S, is the most efficient scale estimator for the normal distribution often used to construct the S control chart, but it is might not be the best choice when one or both assumptions are not met. Therefore, the need for alternatives to the S control chart comes to play. The literatures show that the median absolute deviation from the sample median, MAD, is indeed more resistant to departures from normality and the presence of outliers. In this paper, a univariate robust variable control chart for monitoring the process variability is proposed. The proposed method provides an alternative to the Shewhart S control chart based on the median absolute deviation from the sample median, MAD. This estimator is used to estimate the process standard deviation, σ. The use of the proposed method is illustrated by a numerical example and its performance is investigated through a Monte Carlo simulation study.