FISCAL & SOCIAL STATE
Referent: Jun Zhang
Date & Time: Los Angeles (4 am), Cincinnati (7 am), Bath (12 pm), Munich (1 pm), Beijing (7 pm), Singapore (7 pm) and Sydney (9 pm)
Jun Zhang will present his paper titled "Nonparametric Identification of Bayesian Games (Tullock Contest under Incomplete Information) under Exclusion Restrictions".
Abstract of the paper:
This paper studies the identification problem for Bayesian games (Tullock Contest under Incomplete Information) within the private type paradigm when researchers cannot perfectly know players' payoff structures. We first show that the benchmark framework is not nonparametrically identified without further restrictions. We then impose the exclusion restriction in the form of an exogenous players' participation, and establish nonparametric point or partial identification results. Specifically, we show that if the distributions of actions intersect with each other when the number of players varies, the model primitives, namely, the private type distribution and the unknown structure, are nonparametrically identified up to a scale. Otherwise, they are partially identified as they can be bounded nonparametrically. Our results can be extended to allow for corner solutions, asymmetric players, unobserved heterogeneity, and endogenous participation.
Chair: Lionel Page, Co-Chair: Qiang Fu
Event Team
Max-Planck-Institut für Steuerrecht und Öffentliche Finanzen
Marstallplatz 1
80539 München
Telefon: +49-89-24246-5255
Fax: +49-89-24246-5299
FISCAL & SOCIAL STATE