The speed of sequential asymptotic learning

Wade Hann-Caruthers, Vadim V. Martynov and Omer Tamuz

Papers from arXiv.org

Abstract: In the classical herding literature, agents receive a private signal regarding a binary state of nature, and sequentially choose an action, after observing the actions of their predecessors. When the informativeness of private signals is unbounded, it is known that agents converge to the correct action and correct belief. We study how quickly convergence occurs, and show that it happens more slowly than it does when agents observe signals. However, we also show that the speed of learning from actions can be arbitrarily close to the speed of learning from signals. In particular, the expected time until the agents stop taking the wrong action can be either finite or infinite, depending on the private signal distribution. In the canonical case of Gaussian private signals we calculate the speed of convergence precisely, and show explicitly that, in this case, learning from actions is significantly slower than learning from signals.

Date: 2017-07, Revised 2017-11
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (3)

Published in Journal of Economic Theory, Volume 173, January 2018, Pages 383-409

Downloads: (external link)
http://arxiv.org/pdf/1707.02689 Latest version (application/pdf)

Related works:
Journal Article: The speed of sequential asymptotic learning (2018)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:arx:papers:1707.02689

Access Statistics for this paper

More papers in Papers from arXiv.org
Bibliographic data for series maintained by arXiv administrators ().