òòò½Íø Journal:
Microeconomics
ISSN 1945-7669 (Print) | ISSN 1945-7685 (Online)
Asymptotic Learning with Ambiguous Information
òòò½Íø Journal: Microeconomics
vol. 17,
no. 3, August 2025
(pp. 244–88)
Abstract
We study asymptotic learning when the decision-maker faces ambiguity in the precision of her information sources. She aims to estimate a state and evaluates outcomes according to the worst-case scenario. Under prior-by-prior updating, we characterize the set of asymptotic posteriors the decision-maker entertains, which consists of a continuum of degenerate distributions over an interval. Moreover, her asymptotic estimate of the state is generically incorrect. We show that even a small amount of ambiguity may lead to large estimation errors and illustrate how an econometrician who learns from observing others' actions may over- or underreact to information.Citation
Reshidi, Pëllumb, João Thereze, and Mu Zhang. 2025. "Asymptotic Learning with Ambiguous Information." òòò½Íø Journal: Microeconomics 17 (3): 244–88. DOI: 10.1257/mic.20230142Additional Materials
JEL Classification
- D82 Asymmetric and Private Information; Mechanism Design
- D83 Search; Learning; Information and Knowledge; Communication; Belief; Unawareness