Essays on Empirical Analysis of Continuous-Time Models of Industrial Organization
The dissertation consists of three essays. The first essay describes and estimates the model of bidding on eBay. Internet auctions (such as eBay) differ from the traditional auction format in that participants 1) typically face a choice over several simultaneous auctions and 2) often have limited information about rival bidders. Since existing economic models do not account for these features of the bidding environment, it should not be surprising that even casual empiricism reveals a sharp discrepancy between the predictions of existing theory and the actual behavior of bidders. In this paper, I show that the presence of multiple, contemporaneous auctions for similar items coupled with uncertainty regarding rival entry can explain both features. I analyze these features in a continuous-time stochastic auction model with endogenous entry, in which bidder types are differentiated by their initial information regarding the entry process. Empirical estimates using eBay auctions of pop-music CDs confirm my theoretical prediction that the rate of entry depends on price. I then test my model against alternative explanations of observed bidding behavior using a detailed field experiment.
The second essay is on empirical analysis of executive compensation in the continuous-time environment. In this essay, I develop a methodology for the identification and non-parametric estimation of a continuous-time principal-agent model. My framework extends the existing literature on optimal dynamic contracts by allowing for the presence of unobserved state variables. To accommodate such heterogeneity, I develop an estimation method based on numerically solving for the optimal non-linear manager's response to the restrictions of the contract. To demonstrate this feature, I apply my methodology to executive contracts from the retail apparel industry.
The third essay provides a tractable methodology for the construction and structural estimation of continuous time dynamic models. The specific class of models covered by my framework includes competitive dynamic games where there are no direct spillovers between objective functions of players. I develop an estimation methodology based on the properties of the equilibrium of the model. The methodology that I design can be applied to welfare and revenue analysis of large dynamic models. As an example, I compute the revenue and welfare gains for a counter-factual exercise in which the eBay auction website changes the format of its auctions from second-price to a flexible ending.
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 United States License.
Rights for Collection: Duke Dissertations