GLOBAL ROBUSTNESS WITH RESPECT TO THE LOSS FUNCTION AND THE PRIOR

摘要

We propose a class [I,S] of loss functions for modeling the im- precise preferences of the decision maker in Bayesian Decision Theory. This class is built upon two extreme loss function I and S which reflect the limited information about he loss function. We give an approximation of the set of Bayes actions for every loss function in [I,S] and every prior in a mixture class; if the decision space is a subset of R, we obtain the exact set.