Dynamics of inductive inference in a unified framework

Abstract : We present a model of inductive inference that includes, as special cases, Bayesian reasoning, case-based reasoning, and rule-based reasoning. This unified framework allows us to examine how the various modes of inductive inference can be combined and how their relative weights change endogenously. For example, we establish conditions under which an agent who does not know the structure of the data generating process will decrease, over the course of her reasoning, the weight of credence put on Bayesian vs. non-Bayesian reasoning. We illustrate circumstances under which probabilistic models are used until an unexpected outcome occurs, whereupon the agent resorts to more basic reasoning techniques, such as case-based and rule-based reasoning, until enough data are gathered to formulate a new probabilistic model.
Type de document :
Article dans une revue
Journal of Economic Theory, Elsevier, 2013, 148 (4), pp.1399-1432. 〈10.1016/j.jet.2012.11.004〉
Liste complète des métadonnées

https://hal-hec.archives-ouvertes.fr/hal-00836265
Contributeur : Amaury Bouvet <>
Soumis le : jeudi 20 juin 2013 - 16:32:36
Dernière modification le : jeudi 11 janvier 2018 - 06:19:31

Lien texte intégral

Identifiants

Collections

Citation

Itzhak Gilboa, Larry Samuelson, David Schmeidler. Dynamics of inductive inference in a unified framework. Journal of Economic Theory, Elsevier, 2013, 148 (4), pp.1399-1432. 〈10.1016/j.jet.2012.11.004〉. 〈hal-00836265〉

Partager

Métriques

Consultations de la notice

291