Empirical essays in industrial organization

• Main Author: Chiou, Lesley C
• Other Authors: Glenn Ellison.
• Format: Others
• Language: English
• Published: Massachusetts Institute of Technology 2007
• Subjects: Economics.
• Online Access: http://dspace.mit.edu/handle/1721.1/33838; http://hdl.handle.net/1721.1/33838

Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Economics, 2005. === Includes bibliographical references. === In this dissertation, I present three empirical essays that encompass topics in industrial organization. The first essay examines the degree of competition and spatial differentiation in the retail industry by exploiting a unique dataset that describes a consumer's choice of store, product of purchase, item price, and demographics. I estimate a consumer's choice of retailer in the sales market for DVDs among online, mass merchant, electronics, video specialty, and music stores, and I allow for unobserved heterogeneity in preferences for store types and disutility of travel. A consumer's traveling cost varies by income, and substitution occurs proportionately more among stores of the same type. The second essay investigates an intriguing puzzle in the movie industry: "why do studios cluster their big theatrical hits during the July 4th weekend?" A series of recent papers by Einav (2002) indicate that although the underlying demand for theatrical movies remains high around Labor Day, studios tend to release their high quality movies at the beginning of the summer. I employ data from the home video industry to provide more evidence on whether booms in theatrical revenues are supply- or demand-driven and to investigate why firms might cluster their releases as they do. === (cont.) The third essay presents examples based on actual and synthetic datasets to illustrate how simulation methods can often mask identification problems in the estimation of mixed logit models. Typically, simulation methods approximate an integral (that does not have a closed form) by taking draws from the underlying distribution of the random variable of integration. The examples reveal how a "low" number of draws can generate estimates that appear identified, but in fact, are either not theoretically identified by the model or not empirically identified by the data. The number of draws required to reveal the identification problem will depend on the data, model, and type of draws used. These examples emphasize the importance of checking the stability of the estimates with respect to the number of draws. === by Lesley C. Chiou. === Ph.D.