【主讲】黎晖晖 (Penn State University)
【主题】Nonparametric Identification and Estimation of Double Auctions
【时间】2014年5月29日 (周四) 15：30-17：00
【地点】上海财经大学经济学院楼602室
【语言】英文
【摘要】This paper studies the nonparametric identification and estimation of a useful double auction model, namely k-double auction model. First, we establish the nonparametric identification of both buyer and seller's private value distributions in two bids data scenarios, from the ideal situation where all bids are available to the realistic one where only the transacted bids are available. Specifically, we identify both the buyer and seller's private value distributions when all of the bids can be observed, while we can only partially identify the private value distributions on the support with positive probability of trade when only the traded bids are available in the data. In particular, we show that the conditional private value distributions given probability of trade being positive can be uniquely identified by the distribution of transacted bids. Second, we estimate the double auctions by a two-step procedure with boundary correction. We then establish the uniform convergence rate of such a boundary corrected estimator of the private value distributions on their whole supports.
