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.
Recommendations
Cites work
Cited in
(12)- On the asymptotic behaviour of linear learning processes with partial forgetting
- On the role of responsiveness in rational herds
- Identifiable information structures
- How fragile are information cascades?
- Fast rates by transferring from auxiliary hypotheses
- Fast learning rates in statistical inference through aggregation
- Pathological Outcomes of Observational Learning
- Quickest Search and Learning Over Correlated Sequences: Theory and Application
- Learning from reviews: the selection effect and the speed of learning
- The rates of learning with public and private signals
- Beyond unbounded beliefs: how preferences and information interplay in social learning
- The hazards and benefits of condescension in social learning
This page was built for publication: The speed of sequential asymptotic learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1693201)
