In this paper, I examine methods used to construct and estimate game-t
heoretic models of oligopolistic interactions, and I survey some of th
e empirical findings. Both static and dynamic games are covered. Stati
c models provide useful summary statistics concerning the outcomes of
oligopolistic interaction, whereas dynamic models attempt to capture m
ore complex strategic behaviour. In the exposition of static games, I
consider two empirical approaches: the first-order approach and the du
al approach. When we rum to dynamics, I limit my remarks to state-spac
e games - games in which actions taken in one period shift pay-offs in
subsequent periods. With state-space games, all history that is pay-o
ff relevant is summarized by a small set of variables - the state - an
d players' strategies depend only on the state and time.