Corpus ID: 121298146

Asymptotic Behavior of Bayesian Learners with Misspecified Models

  title={Asymptotic Behavior of Bayesian Learners with Misspecified Models},
  author={Ignacio Esponda and Demian Pouzo},
  journal={arXiv: Theoretical Economics},
  • Ignacio Esponda, Demian Pouzo
  • Published 2019
  • Computer Science, Economics, Mathematics
  • arXiv: Theoretical Economics
  • We consider an agent who represents uncertainty about the environment via a possibly misspecified model. Each period, the agent takes an action, observes a consequence, and uses Bayes' rule to update her belief about the environment. This framework has become increasingly popular in economics to study behavior driven by incorrect or biased beliefs. Current literature has characterized asymptotic behavior under fairly specific assumptions. By first showing that the key element to predict the… CONTINUE READING

    Figures and Topics from this paper.


    Publications referenced by this paper.
    Active learning with a misspecified prior
    • 18
    • PDF
    Informational herding with model misspecification
    • 26
    • PDF
    Macroeconomics with Learning and Misspecification: A General Theory and Applications
    • 11
    Bayesian Networks and Boundedly Rational Expectations
    • 51
    • PDF
    Learning In Mis-Specified Models And The Possibility Of Cycles
    • 61