Bayes reliability measures of Lognormal and inverse Gaussian distributions under ML-II ε-contaminated class of prior distributions

摘要

In this paper we employ ML-II ε-contaminated class of priors to study the sensitivity of Bayes Reliability measures for an Inverse Gaussian (IG) distribution and Lognormal (LN) distribution to misspecification in the prior. The numerical illustrations suggest that reliability measures of both the distributions are not sensitive to moderate amount of misspecification in prior distributions belonging to the class of ML-II ε-contaminated.