Bayesian utilitarianism and probability homogeneity

This paper investigates, within the axiomatic framework of Jeffrey-Bolker decision theory, two kinds of conditions and the relation between them: (1) The Utilitarian condition that social rankings of prospects be representable by an expected utility function that is a weighted sum of the expected utility functions representing individual rankings; and (2) Homogeneity conditions on the probabilities and preferences of individuals. In particular, we show that identity of individuals' probabilities is necessary and sufficient for the Utilitarian condition to hold and that the homogeneity of individuals' probabilities can be derived from a Pareto condition on the relation between individual and social rankings, provided that these rankings are separable in a particular sense.