Econometrics of Auctions and Regulation

PI将研究如何分析在信息不对称的情况下开发的数据。 我们的目标是开发新的方法来进行拍卖模型的结构估计，并将这些方法扩展到合同模型的估计。 在该项目的第一部分，他们将继续其先前关于分析拍卖数据的计量经济学方法的工作。 特别是，他们将开发的方法来估计投标人的效用函数的参数从投标行为的数据。 新方法将用于分析美国林务局木材拍卖的数据。 该项目的第二部分将为估计管制的激励模式制定新的计量经济学方法。 他们将开发完全参数和非参数估计。 这些方法将被用于分析来自公共监管委员会的数据，这些委员会负责管理法国公共交通和加州水务设施。因此，本研究将识别和估计拍卖中的风险规避，并将开发监管模型的计量经济学，同时最大限度地减少每种情况下的先验参数限制。 这些方法将改进行业分析师、监管机构和其他公共政策制定者分析这些市场数据的技术。

The PIs will conduct research on how to analyze data developed in situations of asymmetric information. The goal is to develop new ways to conduct structural estimation of auction models and to extend these methods to the estimation of contract models. In the first part of the project, they will continue their previous work on econometric methods for the analysis of auction data. In particular, they will develop ways to estimate parameters of the bidder's utility function from data on bidding behavior. The new method will be used to analyze data from US Forest Service Timber auctions. The second part of the project will develop new econometric methods for the estimation of incentive models of regulation. They will develop both fully parametric and nonparametric estimators. These methods will be used to analyze data from public regulatory commissions that regulate French public transit and California water utilities.Therefore, this research will identify and estimate risk aversion in auctions and will also develop the econometrics of regulation models, while minimizing prior parametric restrictions in each case. The methods will improve the techniques used by industry analysts, regulators, and other public policy makers to analyze data in these markets.