Stochastic Dominance And Conditional Expectation - An Insurance Theoretical Approach

In English We show that the relation of second order stochastic dominance, which has found widespread use in models of economic behavior under uncertainty, may be described in terms of conditional expectation. If a distribution G second order stochastically dominates another distribution F, then there are random variables g and f with distributions G and F, respectively, such that g can be obtained from f by iterated conditional expectation. In terms of insurance, this shows that the less risky distribution can be obtained by a sequence of insurance contracts each one insuring against the residual risk left over from the previous contracts.