Robust estimators have been developed and tested for symmetric distributions via simulation studies. The primary objective was to show that they are more efficient than the sample mean when used in conjunction with asymmetric distributions. Little attention has been given to how they perform on data that are from asymmetric distributions, or from distributions that have inherent anomalies (messy data). Thus, the behavior of hinge estimators using sensitivity curve are examined.
Stark, D.B. and Reed, J.F. III
"Sensitivity Curves for Asymmetric Trimming Hinge Estimators,"
Journal of Modern Applied Statistical Methods:
2, Article 11.
Available at: http://digitalcommons.wayne.edu/jmasm/vol6/iss2/11