This paper proposes an approach to proving nonparametric identification for distributions of bidders' values in asymmetric second-price auctions. I consider the case when bidders have independent private values and the only available data pertain to the winner's identity and the transaction price. My proof of identification is constructive and is based on establishing the existence and uniqueness of a solution to the system of non-linear differential equations that describes relationships between unknown distribution functions and observable functions. The proof is conducted in two logical steps. First, I prove the existence and uniqueness of a local solution. Then I describe a method that extends this local solution to the whole support. This paper delivers other interesting results. I show how this approach can be applied to obtain identification in more general auction settings, for instance, in auctions with stochastic number of bidders or weaker support conditions. Furthermore, I demonstrate that my results can be extended to generalized competing risks models. Moreover, contrary to results in classical competing risks (Roy model), I show that in this generalized class of models it is possible to obtain implications that can be used to check whether the risks in a model are dependent. Finally, I provide a sieve minimum distance estimator and show that it consistently estimates the underlying valuation distribution of interest.
We propose a novel methodology for nonparametric identification of first-price auction models with independent private values, which allows for one-dimensional auction-specific unobserved heterogeneity, based on recent results from the econometric literature on nonclassical measurement error in Hu and Schennach (2008). Our approach can accommodate a wide variety of applications in which some location of the conditional distribution of bids (e.g. min or max of the support, mean, etc.) is increasing in the unobserved heterogeneity. This includes settings in which the econometrician fails to observe the reserve price, the cost of bidding, the number of bidders, or some factor (“quality”) with a non-linear effect on bidder values.
My dissertation contributes to the structural nonparametric econometrics of auctions and contests with incomplete information. It consists of three chapters. The first chapter investigates the identification and estimation of an all-pay auction where the object is allocated to the player with the highest bid, and every bidder pays his bid regardless of whether he wins or not. As a baseline model, I consider the setting, where one object is allocated among several risk-neutral participants with independent private values (IPV); however, I also show how the model can be extended to the multiunit case. Moreover, the model is not confined to the IPV paradigm, and I further consider the case where the bidders' private values are affiliated (APV). In both IPV and APV settings, I prove the identification and derive the consistent estimators of the distribution of the bidders' valuations using a structural approach similar to that of Guerre et al. (2000). Finally, I consider the model with risk-averse bidders. I prove that in general the model in this set-up is not identified even in the semi-parametric case where the utility function of the bidders is restricted to belong to the class of functions with constant absolute risk aversion (CARA). The second chapter proves the identification and derives the asymptotically normal estimator of a nonparametric contest of incomplete information with uncertainty. By uncertainty, I mean that the contest success function is not only determined by the bids of the players, but also by the variable, which I call uncertainty, with a nonparametric distribution, unknown to the researcher, but known to the bidders. This work is the first to consider the incomplete information contest with a nonparametric contest success function. The limiting case of the model when there is no uncertainty is an all-pay auction considered in the first chapter. The model with two asymmetric players is examined. First, I recover the distribution of uncertainty using the information on win outcomes and bids. Next, I adopt the structural approach of Guerre et al. (2000) to obtain the distribution of the bidders' valuations (or types). As an empirical application, I study the U.S. House of Representatives elections. The model provides a method to disentangle two sources of incumbency advantage: a better reputation, and better campaign financing. The former is characterized by the distribution of uncertainty and the latter by the difference in the distributions of candidates' types. Besides, two counterfactual analyses are performed: I show that the limiting expenditure dominates public campaign financing in terms of lowering total campaign spending as well as the incumbent's winning probability. The third chapter is a semiparametric version of the second chapter. In the case when the data is sparse, some restrictions on the nonparametric structure need to be put. In this work, I prove the identification and derive the consistent estimator of a contest of incomplete information, in which an object is allocated according to the serial contest success function. As in previous chapters, I recover the distribution of the bidders' valuations from the data on observed bids using a structural approach similar to that of Guerre et al. (2000) and He and Huang (2018). As a baseline model, I consider the symmetric contest. Further, the model is extended to account for the bidders' asymmetry.
This dissertation contributes to the structural auction literature in two different auction models, namely the pure common value model and the affiliated private value model. The goal of structural analysis of auction data is to recover the model primitives and to provide policy guidance for welfare analysis. In Chapter 1, we study identification in the first-price and the second-price sealed-bid auctions within the pure common value framework. In Chapter 2, we apply the identification results and estimation method in Chapter 1 to analyze the U.S. Outer Continental Shelf (OCS) wildcat auction data and provide policy guidance for welfare analysis. In Chapter 3, we develop identification and partial identification results for the first-price and the second-price sealed-bid auction models with affiliated private values and incomplete sets of bids. Chapter 1: In this chapter, we establish novel identification results for both the first-price and the second-price sealed-bid auction models within the pure common value framework. We show that the policy parameters, including the expected total welfare, the seller's expected revenue, and the bidders' expected surplus under any reserve price are identified for a general nonparametric class of latent joint distributions when the ex-post common value is unobserved. Moreover, we establish that these policy parameters are nonparametric identified without normalization assumption when the ex-post common value is observed. We propose a semiparametric estimation method and establish consistency of the estimator. Results from Monte Carlo experiments reveal good finite sample performance of the estimator. Chapter 2: In this chapter, we employ the identification strategy and estimation method in Chapter 1 to analyze data from the U.S. Outer Continental Shelf (OCS) wildcat auctions in the pure common value framework. We study the welfare implication of different counterfactual reserve prices, focusing on the cases with two and three bidders. The empirical results suggest that if the U.S. government had set reserve prices optimally using the newly-developed econometric method in Chapter 1, its expected revenue can be increased by around $34\%$ and $30\%$ for these two cases, respectively. Lastly, we compare our results with those estimated under the affiliated private value framework, and find that the estimated welfare curves under the two different frameworks are very different. Chapter 3: In this chapter, we address the identification issue in the first-price sealed-bid affiliated private value model when an incomplete set of bids is observed. In the simple case with symmetric bidders and non-binding reserve price, we establish identification or partial identification results in two scenarios of practical interest. First, when the two highest bids are observed, we achieve identification of the joint distribution function of private values by assuming the copula function of private values to be a nonparametric Archimedean copula with weak requirement. Second, when only the highest bid is observed, we establish partial identification for the quantile function of private value and several policy parameters by parameterizing the copula function. Further, we extend the identification/partial identification results to the cases with asymmetric bidders and/or binding reserve price. We also extend our identification/partial identification results to the second-price sealed-bid auction.
This dissertation consists of two chapters on nonparametrically identifying and estimating the sealed-bid k-double auction models between single buyer and single seller.Chapter 1: Nonparametric Identification and Estimation of k-Double Auctions Using Bid DataThis chapter studies the nonparametric identification and estimation of double auctions with one buyer and one seller. This model assumes that both bidders submit their own sealed bids, and the transaction price is determined by a weighted average between the submitted bids when the buyers offer is higher than the sellers ask. It captures the bargaining process between two parties. Working within this double auction model, we first establish the nonparametric identification of both the buyers and the sellers private value distributions in two bid data scenarios; from the ideal situation in which all bids are available, to a more realistic setting in which only the transacted bids are available. Specifically, we can identify both private value distributions when all of the bids are observed. However, we can only partially identify the private value distributions on the support with positive (conditional) probability of trade when only the transacted bids are available in the data. Second, we estimate double auctions with bargaining using a two-step procedure that incorporates bias correction. We then show that our value density estimator achieves the same uniform convergence rate as Guerre, Perrigne, and Vuong (2000) for one-sided auctions. Monte Carlo experiments show that, in finite samples, our estimation procedure works well on the whole support and significantly reduces the large bias of the standard estimator without bias correction in both interior and boundary regions.Chapter 2: Nonparametric Identification of k-Double Auctions Using Price DataThis chapter studies the model identification problem of k-double auctions between one buyer and one seller when the transaction price, rather than the traders bids, can be observed. Given that only the price data is available, I explore an identification strategy that utilizes the double auctions with extreme pricing weight (k=1 or 0) and exclusive covariates that shift only one traders value distribution to identify both the buyers and the sellers value distributions nonparametrically. First, as each exclusive covariate can take at least two values, the buyers and the sellers value distributions are partially identified from the price distribution for k=1 or k=0. The identified set is sharp and can be easily computed. I provide a set of sufficient conditions under which the traders value distributions are point identified. Second, when the exclusive covariates are continuous, it is shown that the buyers and the sellers value distributions will be uniquely determined by a partial differential equation that only depends on the price distribution, provided that the value distributions are known for at least one value of the exclusive covariates.
Handbook of Computational Economics summarizes recent advances in economic thought, revealing some of the potential offered by modern computational methods. With computational power increasing in hardware and algorithms, many economists are closing the gap between economic practice and the frontiers of computational mathematics. In their efforts to accelerate the incorporation of computational power into mainstream research, contributors to this volume update the improvements in algorithms that have sharpened econometric tools, solution methods for dynamic optimization and equilibrium models, and applications to public finance, macroeconomics, and auctions. They also cover the switch to massive parallelism in the creation of more powerful computers, with advances in the development of high-power and high-throughput computing. Much more can be done to expand the value of computational modeling in economics. In conjunction with volume one (1996) and volume two (2006), this volume offers a remarkable picture of the recent development of economics as a science as well as an exciting preview of its future potential. Samples different styles and approaches, reflecting the breadth of computational economics as practiced today Focuses on problems with few well-developed solutions in the literature of other disciplines Emphasizes the potential for increasing the value of computational modeling in economics
We present new identification results for models of first-price, second-price, ascending (English), and descending (Dutch) auctions. We analyze a general specification of bidders' preferences and the underlying information structure, nesting as special cases the pure private values and pure common values models, and allowing both ex ante symmetric and asymmetric bidders. We address identification of a series of such models and propose strategies for discriminating between them on the basis of observed data. In the simplest case, the symmetric independent private values model is nonparametrically identified even if only the transaction price from each auction is observed. For more complex models, we provide conditions for identification and testing when additional information of one of the following types is available: (i) one or more bids in addition to the transaction price; (ii) exogenous variation in the number of bidders; (iii) bidder-specific covariates that shift the distribution of valuations; (iv) the ex post realization of the value of the object sold. Our results include new tests that distinguish between private and common values models.
