Abstract

Accurate elicitation of expert's subjective beliefs is known to be challenging. Undertaking a prior robustness analysis by using an appropriate class of prior distributions is therefore recommended. The aim of any robust Bayesian analysis is to get a quantity of interest spanning a small range as the prior distribution varies in the class. We present a new approach based on Decision Analysis which models the competing goals of shrinking the entertained class removing otherwise acceptable priors and achieving smaller ranges.