We study the degree of falsifiability of theories of choice. A theory is easy to falsify if relatively small datasets are enough to guarantee that the theory can be falsified: the VC dimension of a theory is the largest sample size for which the theory is ''never falsifiable.'' VC dimension is...

Consider a society where ethnic conflict is imminent due to people's belief about the state of the world. An `informed agent' is a player who has private information about the state. We analyze whether the informed agent can achieve peace by sending private messages to the players. If the...

We study a repeated game with payoff externalities and observable actions where two players receive information over time about an underlying payoff-relevant state, and strategically coordinate their actions. Players learn about the true state from private signals, as well as the actions of...

In this paper, we study a non-parametric approach to prediction in stochastic choice models in economics. We apply techniques from statistical learning theory to study the problem of learning choice probabilities. A model of stochastic choice is said to be learnable if there exist learning rules...

We study a setting in which a mechanism designer must choose the appropriate social alternative depending on the state of nature. We study the problem of optimal design and demonstrate that a mechanism that allocates the social optimum and assigns payments equal to the posterior expected utility...

We study the degree of falsifiability of theories of choice. A theory is easy to falsify if relatively small datasets are enough to guarantee that the theory can be falsified: the VC dimension of a theory is the largest sample size for which the theory is ''never falsifiable.'' VC dimension is...

We study a setting in which a mechanism designer must choose the appropriate social alternative depending on the state of nature. We study the problem of optimal design and demonstrate that a mechanism that allocates the social optimum and assigns payments equal to the posterior expected utility...

We consider a setting in which additional parameters that determine preference characteristics is 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...