Masking effect on tests for outliers in normal samples

Abstract

Bendre & Kale (1985) defined the masking effect on tests for outliers by the loss in power due to the presence of more than the number of outliers under test. Using the same measure, the limiting masking effects on outlier tests such as the Grubbs, Ferguson and Dixon tests are investigated. Ferguson's test based on sample skewness is more robust against the masking effect than the others.