Econometrics on interactions-based models: Methods and applications.

详细信息   

• 作者：Liu ; Xiaodong.
• 学历：Doctor
• 年：2007
• 导师：Lee, Lung-fei
• 毕业院校：Ohio State University
• 专业：Economics, General.
• ISBN：9780549000181
• CBH：3262096
• Country：USA
• 语种：English
• FileSize：6728223
• Pages：181

文摘

My dissertation research emphasizes estimation methods in evaluating the extent of social, strategic and spatial interactions among economic agents. Topical applications include measuring peer group effects in experimental signaling games, structural estimation of the latent value distribution through bidder's strategic bidding behavior in empirical auctions, and GMM estimation of spatial autoregressive models.;My first essay, based on my joint research with Lung-fei Lee and John Kagel, generalizes Heckman's (1981) dynamic discrete-choice panel data models by introducing timelagged social interactions so that the models can accommodate relationships of decision making across cross-sectional units. We derive the likelihood function for the generalized model and propose simulation based methods to implement the maximum likelihood estimation. Such dynamic social interaction models may have broad applicability, especially in interpreting experimental economics data. In this essay, we use this model to investigate learning from peers in experiments based on Milgrom and Roberts' (1982) entry limit pricing game. We find that subjects' decisions are significantly influenced by the past decisions of their peers in the experiment. Our findings are consistent with the view that the imitation of peers' strategies is an important component of one's learning how to play strategically. Similar peer group effects are likely to be present in experimental designs where subjects receive feedback on their peer's performance.;My second essay explores the robustness of Guerre, Perrigne and Vuong's (2000) two-step nonparametric estimation procedure in auctions with a large number of risk-averse bidders. Guerre et al. show that the underlying distribution of bidders' values (or costs) is nonparametrically identified from the observation of submitted bids when the auction among risk-neutral bidders is conducted as a first-price, sealed-bid auction under the independent private value paradigm. They propose a two-step nonparametric estimation procedure for the latent value distribution based on the equilibrium bidding behavior of risk-neutral bidders. Their estimator is optimal in terms of uniform convergence rate to the true distribution. In this essay, with an asymptotic approximation of the intractable equilibrium bidding function of risk-averse bidders, I demonstrate that Guerre et al.'s two-step nonparametric estimator is still uniformly consistent even if bidders are risk-averse as long as the number of players in an auction is sufficiently large and derive the uniform convergence rate of the estimator. Furthermore, I show in Monte Carlo experiments that the two-step nonparametric estimator performs reasonably well with a moderate number of risk-averse bidders like six.;In my third essay, which is based on my joint research with Lung-fei Lee and Christopher Bollinger, we consider the GMM estimation of the regression model with spatial autoregressive disturbances and the mixed-regressive spatial autoregressive model. We derive the best GMM estimator within the class of GMM estimators that are based on linear and quadratic moment conditions. Our best GMM estimator has the merit of computational simplicity and asymptotic efficiency. We show that it is asymptotically as efficient as the conventional maximum likelihood estimator under normality and asymptotically more efficient than the quasi-maximum likelihood estimator when the normality assumption does not hold. We show in Monte Carlo studies that, with moderate sample sizes, the proposed best GMM estimator has its biggest advantage when the disturbances are asymmetrically distributed. In the event that the diagonal elements from the squared spatial weights matrix have sufficient variance, then incorporating the kurtosis of the disturbances in the moment conditions of the GMM estimator will also be valuable.