Research

This paper develops a flexible discrete-choice demand framework for aggregate data sets that extends Berry, Levinsohn, and Pakes (1995) and the Pure Characteristics Demand Model of Berry and Pakes (2007). I provide a simple, computationally tractable, asymptotically normal estimator based on two contributions: a globally-convergent algorithm to recover utilities from observed demand and a Quasi-Bayes approach that minimizes simulation variance. The framework accommodates zero market shares, which are a challenge for alternative approaches. I show that zeros in demand generate an endogenously censored model, which leads to moment inequalities. As an application, I study moving costs US internal migration data.

This paper explores optimal distributive policies using a Collective approach to household behavior. This approach allows individual preferences for each spouse, which is crucial when examining policies targeted to women, like Mexico’s Prospera or Brazil’s Bolsa Família programs. We assume the spouses’ decisions follow a Nash-bargaining procedure with internal threat points. We show that the taxation principle does not apply, meaning that the optimal tax schedule is dominated by the optimal mechanism. This is because a single tax schedule cannot optimally influence threat points and induce households to choose desired allocations simultaneously. By permitting couples to opt for joint or individual tax filing, we significantly increase the set of implementable allocations. The central role of threat points motivates an extension of the model in which marriage market negotiations partially determine threat points after marriage. This extension endogenizes the distribution of couples and formalizes how general equilibrium considerations and social norms affect bargaining power within a couple. The extended model generalizes previous approaches to the optimal taxation of couples. Finally, we parametrize and calibrate this model to empirically evaluate the relevance of our theoretical findings. The ability to influence threat points has large effects on equilibrium allocations and the evaluation of optimal policies.