Measuring Stochastic Rationality

Abstract

Our goal is to develop a partial ordering method for comparing stochastic choice functions on the basis of their individual rationality. To this end, we assign to any stochastic choice function a one-parameter class of deterministic choice correspondences, and then check for the rationality (in the sense of revealed preference) of these correspondences for each parameter value. The resulting ordering detects violations of (stochastic) transitivity as well as inconsistencies between choices from nested menus. We obtain a parameter-free characterization and apply it to some popular stochastic choice models. We also provide empirical applications in terms of two well-known choice experiments.