Rationalizable learning

Andrew Caplin; Daniel Martin; Philip Marx

doi:10.1007/s00199-024-01627-z

Rationalizable learning

Andrew Caplin, Daniel Martin, Philip Marx

Research output: Contribution to journal › Article › peer-review

Abstract

The central question we address in this paper is: what can an analyst infer from choice data about what a decision maker has learned? The key constraint we impose, which is shared across models of Bayesian learning, is that any learning must be rationalizable. We use our framework to show how identification can be strengthened as one imposes the assumptions behind more restrictive forms of Bayesian learning.

Original language	English (US)
Journal	Economic Theory
DOIs	https://doi.org/10.1007/s00199-024-01627-z
State	Accepted/In press - 2025

Keywords

Identification
Information acquisition
Learning
Rational inattention
Revealed preference
Stochastic choice

ASJC Scopus subject areas

Economics and Econometrics

Access to Document

10.1007/s00199-024-01627-z

Cite this

@article{4edc1f21ce014377898b4f63be1ab0fa,

title = "Rationalizable learning",

abstract = "The central question we address in this paper is: what can an analyst infer from choice data about what a decision maker has learned? The key constraint we impose, which is shared across models of Bayesian learning, is that any learning must be rationalizable. We use our framework to show how identification can be strengthened as one imposes the assumptions behind more restrictive forms of Bayesian learning.",

keywords = "Identification, Information acquisition, Learning, Rational inattention, Revealed preference, Stochastic choice",

author = "Andrew Caplin and Daniel Martin and Philip Marx",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.",

year = "2025",

doi = "10.1007/s00199-024-01627-z",

language = "English (US)",

journal = "Economic Theory",

issn = "0938-2259",

publisher = "Springer New York",

}

TY - JOUR

T1 - Rationalizable learning

AU - Caplin, Andrew

AU - Martin, Daniel

AU - Marx, Philip

N1 - Publisher Copyright: © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

PY - 2025

Y1 - 2025

N2 - The central question we address in this paper is: what can an analyst infer from choice data about what a decision maker has learned? The key constraint we impose, which is shared across models of Bayesian learning, is that any learning must be rationalizable. We use our framework to show how identification can be strengthened as one imposes the assumptions behind more restrictive forms of Bayesian learning.

AB - The central question we address in this paper is: what can an analyst infer from choice data about what a decision maker has learned? The key constraint we impose, which is shared across models of Bayesian learning, is that any learning must be rationalizable. We use our framework to show how identification can be strengthened as one imposes the assumptions behind more restrictive forms of Bayesian learning.

KW - Identification

KW - Information acquisition

KW - Learning

KW - Rational inattention

KW - Revealed preference

KW - Stochastic choice

UR - http://www.scopus.com/inward/record.url?scp=85213712445&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85213712445&partnerID=8YFLogxK

U2 - 10.1007/s00199-024-01627-z

DO - 10.1007/s00199-024-01627-z

M3 - Article

AN - SCOPUS:85213712445

SN - 0938-2259

JO - Economic Theory

JF - Economic Theory

ER -

Rationalizable learning

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this