Multiplicity of equilibria and information structures in empirical games: challenges and prospects
- PDF / 212,245 Bytes
- 11 Pages / 439.37 x 666.142 pts Page_size
- 28 Downloads / 137 Views
Multiplicity of equilibria and information structures in empirical games: challenges and prospects Session at the 9th Triennial Choice Symposium Ron N. Borkovsky & Paul B. Ellickson & Brett R. Gordon & Victor Aguirregabiria & Pedro Gardete & Paul Grieco & Todd Gureckis & Teck-Hua Ho & Laurent Mathevet & Andrew Sweeting
# Springer Science+Business Media New York 2014
Abstract Empirical models of strategic games are central to much analysis in marketing and economics. However, two challenges in applying these models to real-world data are that such models often admit multiple equilibria and that they require strong Ron N. Borkovsky, Paul B. Ellickson and Brett R. Gordon were the co-chairs of the session at the 9th Triennial Choice Symposium.
R. N. Borkovsky (*) : V. Aguirregabiria University of Toronto, Toronto, Canada e-mail: [email protected] V. Aguirregabiria e-mail: [email protected]
P. B. Ellickson University of Rochester, Rochester, NY, USA e-mail: [email protected] B. R. Gordon Columbia Business School, New York, NY, USA e-mail: [email protected] P. Gardete Stanford University, Stanford, CA, USA e-mail: [email protected] P. Grieco Pennsylvania State University, State College, PA, USA e-mail: [email protected] T. Gureckis : L. Mathevet New York University, New York, NY, USA T. Gureckis e-mail: [email protected] L. Mathevet e-mail: [email protected]
Mark Lett
informational assumptions. The first implies that the model does not make unique predictions about the data, and the second implies that results may be driven by strong a priori assumptions about the informational setup. This article summarizes recent work that seeks to address both issues and suggests some avenues for future research. Keywords Static discrete games . Dynamic games . Structural estimation . Multiplicity of equilibria . Information structures . Learning
1 Introduction Structural estimation of strategic games has allowed researchers to address a wide variety of important questions about competitive conduct in concentrated markets. The early literature—spawned by Bresnahan and Reiss (1991)—restricted attention to static discrete games, i.e., one-shot games in which each firm faces a finite set of possible actions. This framework has been used to study entry, pricing formats, product lines, product quality, and store format and location in oligopolistic settings. Ericson and Pakes (1995) introduced an estimable model of dynamic competition that built upon the static discrete games literature in two ways. First, it incorporated forward-looking firms that interact repeatedly, allowing researchers to examine richer industry behavior. Second, it allowed firms to make not only discrete but also continuous choices. Resulting models consider dynamic pricing, R&D investment, and advertising outlays, among other topics. Despite tremendous progress over the past decade, these related literatures continue to face similar challenges. First, the possibility of multiple equilibria poses challenges for
Data Loading...
