Identification and Estimation of Dynamic Games

Abstract

This paper studies the identification problem in infinite horizon Markovian games and proposes a generally applicable estimation method. Every period firms simultaneously select an action from a finite set. We characterize the set of Markov equilibria. Period profits are a linear function of equilibrium choice probabilities. The question of identification of these values is then reduced to the existence of a solution to this linear equation system. We characterize the identification conditions.We propose a simple estimation procedure which follows the steps in the identification argument.The estimator is consistent, asymptotic normally distributed, and efficient.We have collected quarterly time series data on pubs, restaurants, coffeehouses, bakeries and carpenters for two Austrian towns between 1982 and 2002. A dynamic entry game is estimated in which firms simultaneously decide whether to enter, remain active, or exit the industry. The period profit estimates are used to simulate the equilibrium behavior under a policy experiment in which a unit tax is imposed on firms deciding to enter the industry.

Differentiation Across Standards and Adoption Failure in 56K Modems

“…We show that ISP's split much more evenly than independent random choice would predict with the dartboard index of Ellison and Glaeser (1997). We confirm this result in a bivariate probit frame- 30 Shapiro and Varian suggest a faster diffusion process then we do prior to the ITU decision, relying mostly on announced adoption decisions for source material. Most of these announcements come from the medium to large firms.…”

“…However, they do not offer a detailed explanation of why there was adoption failure previous to the ITU decision and do not consider incentives to differentiate across the standards by ISPs. 30 …”

An Estimable Demand System for a Large Auction Platform Market

“…Recall that an equilibrium bid strategy for a type x is a bid in each state, and 15 A similar identification argument was made in a different context by Pesendorfer and Schmidt-Dengler (2003).…”

Last-In First-Out Oligopoly Dynamics

“…It allows for a wide variety of dynamic investment decisions, but there is no characterization of its equilibrium set beyond the existence proof due to Doraszelski and Satterthwaite (2005). Accordingly, the estimation of this framework's unknown parameters either occurs "off-line", as in Benkard (2004), or by considering each firm's decision problem in isolation and letting the data reveal which equilibrium was played in sample, as in Bajari et al (2006) and Pesendorfer and Schmidt-Dengler (2003). Strictly speaking, the Ericson and Pakes framework encompasses our model, but we abstract from its most compelling feature, technological change arising from investment decisions.…”