Standard incentive theory models provide a rich framework for studying informational Incentive problems arise in many economic relationships. Contracts that tie compensation to performance can mitigate incentive problems, but writing completely effective contracts is often impractical.1 As a result, real-world incentives frequently are informal. Within firms, compensation and promotion often are based on difficult to verify aspects of performance such as teamwork, leadership, or initiative. Employees understand this without the precise details being codified in a formal contract and firms live up to their promises because they care about their labor market reputation.2 Similarly, firms often expect a level of flexibility and adaptation from suppliers that goes well beyond contractual requirements. The give and take of the relationship allows prices or details of delivery to adjust in response to specific circumstances. The need for a relational contract is a matter of degree. Sovereign nations comply with trade agreements and repay foreign debt because they desire the continued goodwill of trading partners. Politicians have an incentive to assist large donors because they will need to raise money in future campaigns. On the other hand, when a firm contracts with its employees or other firms, or when a government agency regulates an industry, a formal contract may provide a reasonable starting point. In these cases, good faith allows for more flexibility and nuance in incorporating information.Information plays the same role in relational contracting as in standard incentive theory. Better performance measures generate more effective incentives. But a relational contract can incorporate a much broader range of subjective information. For instance, the best gauge of employee performance is often the subjective evaluations of peers or supervisors. Firms regularly use such measures for compensation and promotion decisions. In a survey of law firm compensation by the consulting firm Altman Weil, Inc., 50 percent of law firms report using

We describe a two-step algorithm for estimating dynamic games under the assumption that behavior is consistent with Markov perfect equilibrium. In the first step, the policy functions and the law of motion for the state variables are estimated. In the second step, the remaining structural parameters are estimated using the optimality conditions for equilibrium. The second step estimator is a simple simulated minimum distance estimator. The algorithm applies to a broad class of models, including industry competition models with both discrete and continuous controls such as the Ericson and Pakes (1995) model. We test the algorithm on a class of dynamic discrete choice models with normally distributed errors and a class of dynamic oligopoly models similar to that of Pakes and McGuire (1994).

The quality and quantity of data on economic activity are expanding rapidly. Empirical research increasingly relies on newly available large-scale administrative data or private sector data that often is obtained through collaboration with private firms. Here we highlight some challenges in accessing and using these new data. We also discuss how new data sets may change the statistical methods used by economists and the types of questions posed in empirical research.