Rationalizable learning

B-Tier
Journal: Economic Theory
Year: 2025
Volume: 80
Issue: 1
Pages: 171-202

Authors (3)

Andrew Caplin (not in RePEc) Daniel Martin (Northwestern University) Philip Marx (not in RePEc)

Score contribution per author:

0.673 = (α=2.02 / 3 authors) × 1.0x B-tier

α: calibrated so average coauthorship-adjusted count equals average raw count

Abstract

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.

Technical Details

RePEc Handle
repec:spr:joecth:v:80:y:2025:i:1:d:10.1007_s00199-024-01627-z
Journal Field
Theory
Author Count
3
Added to Database
2026-01-25