Convergence in Misspecified Learning Models with Endogenous Actions

23 Pages Posted: 14 Jan 2019

See all articles by Paul Heidhues

Paul Heidhues

Heinrich Heine University Dusseldorf - Duesseldorf Institute for Competition Economics (DICE)

Botond Koszegi

Central European University (CEU) - Department of Economics

Philipp Strack

Yale, Department of Economics

Date Written: December 6, 2018

Abstract

We establish convergence of beliefs and actions in a class of one-dimensional learning settings in which the agent’s model is misspecified, she chooses actions endogenously, and the actions affect how she misinterprets information. The crucial assumptions of our model are that the state and action spaces are continuous, the state has a unidirectional effect on output, and the prior and noise are normal. These assumptions imply that the agent’s posterior admits a one-dimensional summary statistic, allowing us to apply tools from stochastic approximation theory to establish convergence. Applications of our framework include learning by a person who has an incorrect model of a technology she uses, is subject to confirmatory bias, conservatism, or base-rate neglect, or is overconfident about herself, learning by a representative agent who misunderstands macroeconomic outcomes, as well as learning by a firm that has an incorrect parametric model of demand.

Suggested Citation

Heidhues, Paul and Koszegi, Botond and Strack, Philipp, Convergence in Misspecified Learning Models with Endogenous Actions (December 6, 2018). Available at SSRN: https://ssrn.com/abstract=3312968 or http://dx.doi.org/10.2139/ssrn.3312968

Paul Heidhues

Heinrich Heine University Dusseldorf - Duesseldorf Institute for Competition Economics (DICE)

Universitaetsstr. 1
Duesseldorf, NRW 40225
Germany

Botond Koszegi

Central European University (CEU) - Department of Economics ( email )

Nador u. 9.
Budapest H-1051
Hungary

Philipp Strack (Contact Author)

Yale, Department of Economics ( email )

28 Hillhouse Ave
New Haven, CT 06520-8268
United States

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
136
Abstract Views
731
rank
229,063
PlumX Metrics