Abstract
We consider a setting in which additional parameters that determine preference characteristics are unknown. The mechanism designer specifies a model for possible type distributions and utility functions. We consider mechanisms that are uniformly incentive compatible with respect to a domain of possible utility functions. We identify conditions on the utility domain in which mechanisms always prescribe the same distribution over outcomes. These conditions have implications for optimal mechanism design with max-min objectives, and may be interpreted as capturing different forms of preference heterogeneity.