This paper examines the bidding for school milk contracts in Florida and Texas during the 1980s. In both states firms were convicted of bid-rigging. The data and legal evidence suggest that the cartels in the two states allocate contracts in different ways: One cartel divides the market among members, while the other cartel also uses side payments to compensate members for refraining from bidding. We show that both forms of cartel agreements are almost optimal, provided the number of contracts is sufficiently large. In the auction the cartel bidder may face competition from non-cartel bidders. The presence of an optimal cartel induces an asymmetry in the auction. The selected cartel bidder is bidding as a representative of a group and has on average a lower cost than a non-cartel bidder. The data support the predicted equilibrium bidding behaviour in asymmetric auctions in accordance with optimal cartels.

This paper considers the estimation problem in dynamic games with finite actions. we derive the equation system that characterizes the markovian equilibria. the equilibrium equation system enables us to characterize conditions for identification. we consider a class of asymptotic least squares estimators defined by the equilibrium conditions. this class provides a unified framework for a number of well-known estimators including those by Hotz and Miller (1993) and by Aguirregabiria and Mira (2002). We show that these estimators differ in the weight they assign to individual equilibrium conditions. We derive the efficient weight matrix. A Monte Carlo study illustrates the small sample performance and computational feasibility of alternative estimators.

Recursive procedures which are based on iterating on the best response mapping have difficulties converging to all equilibria in multi-player games. We illustrate these difficulties by revisiting the asymptotic properties of the iterative nested pseudo maximum likelihood method for estimating dynamic games introduced by Aguirregabiria and Mira (2007). An example shows that the iterative method may not be consistent.