A simple class of models for possibly contaminated data is considered, for which the effect of large observations on our beliefs and on our procedures is small. Various properties are derived, and the effects of differing prior opinions are considered.
Michael Goldstein. "Contamination Distributions." Ann. Statist. 10 (1) 174 - 183, March, 1982. https://doi.org/10.1214/aos/1176345699