Convergence to Rational Expectations in a Stationary Linear Game.

Jordan, J. S.

This paper describes several learning processes which converge, with probability one, to the rational expectations Bayesian-Nash) equilibrium of a stationary linear game. The learning processes include a test for convergence to equilibrium, and a method for changing the parameters of the process when non-convergence is indicated. This self-stabilization property eliminates the need to impose stability conditions on the economic environment. Convergence to equilibrium is proved for two types of self-stabilizing learning mechanisms: a centralized forecasting mechanism and a decentralized strategy adjustment process.

ECONOMIC equilibrium; LEARNING; FORECASTING; PROBABILITY theory; BAYESIAN analysis; ECONOMIC stabilization; EQUILIBRIUM; STOCHASTIC convergence; MATHEMATICS

Review of Economic Studies, 1992, Vol 59, Issue 1, p109

0034-6527

Academic Journal

10.2307/2297928