Conditionalization

Convex sets of conditional distributions are used to represent conditional beliefs. Inference is performed by applying Bayes rule to each distribution in a jont credal set. The posterior credal set is the union of all posterior distributions obtained in this process, and the vertices of the posterior credal set are obtained by applying Bayes rule to all vertices of the joint credal set [28]. Denote by K(X|Y) the collection of credal sets K(X|A) for all events A defined by a variable Y.