Parameter estimates used in control charting, the sample mean and variance, are based on maximum likelihood estimation (MLE). Unfortunately, MLEs are not robust to contaminated data and can lead to improper conclusions regarding parameter values. This article proposes a more robust estimation technique; the minimized integrated square error estimator (L2E).
Dyer, John N.
"A Simulation Study of the Relative Efficiency of the Minimized Integrated Square Error Estimator (L2E) For Phase I Control Charting,"
Journal of Modern Applied Statistical Methods:
1, Article 27.
Available at: http://digitalcommons.wayne.edu/jmasm/vol10/iss1/27