Learning the fundamentals in a stationary environment

Nabil I. Al-Najjar; Eran Shmaya

doi:10.1016/j.geb.2018.02.007

Learning the fundamentals in a stationary environment

Nabil I. Al-Najjar^*, Eran Shmaya

^*Corresponding author for this work

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

1 Scopus citations

Abstract

A Bayesian agent relies on past observations to learn the structure of a stationary process. We show that the agent's predictions about near-horizon events become arbitrarily close to those he would have made if he knew the long-run empirical frequencies of the process.

Original language	English (US)
Pages (from-to)	616-624
Number of pages	9
Journal	Games and Economic Behavior
Volume	109
DOIs	https://doi.org/10.1016/j.geb.2018.02.007
State	Published - May 2018

Keywords

Learning
Merging
Stationarity

ASJC Scopus subject areas

Finance
Economics and Econometrics

Access to Document

10.1016/j.geb.2018.02.007

Cite this

@article{e8a27533c0b74ba2ba10ab466e963629,

title = "Learning the fundamentals in a stationary environment",

abstract = "A Bayesian agent relies on past observations to learn the structure of a stationary process. We show that the agent's predictions about near-horizon events become arbitrarily close to those he would have made if he knew the long-run empirical frequencies of the process.",

keywords = "Learning, Merging, Stationarity",

author = "Al-Najjar, {Nabil I.} and Eran Shmaya",

note = "Publisher Copyright: {\textcopyright} 2018 Elsevier Inc.",

year = "2018",

month = may,

doi = "10.1016/j.geb.2018.02.007",

language = "English (US)",

volume = "109",

pages = "616--624",

journal = "Games and Economic Behavior",

issn = "0899-8256",

publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Learning the fundamentals in a stationary environment

AU - Al-Najjar, Nabil I.

AU - Shmaya, Eran

PY - 2018/5

Y1 - 2018/5

N2 - A Bayesian agent relies on past observations to learn the structure of a stationary process. We show that the agent's predictions about near-horizon events become arbitrarily close to those he would have made if he knew the long-run empirical frequencies of the process.

AB - A Bayesian agent relies on past observations to learn the structure of a stationary process. We show that the agent's predictions about near-horizon events become arbitrarily close to those he would have made if he knew the long-run empirical frequencies of the process.

KW - Learning

KW - Merging

KW - Stationarity

UR - http://www.scopus.com/inward/record.url?scp=85044133736&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044133736&partnerID=8YFLogxK

U2 - 10.1016/j.geb.2018.02.007

DO - 10.1016/j.geb.2018.02.007

M3 - Article

AN - SCOPUS:85044133736

SN - 0899-8256

VL - 109

SP - 616

EP - 624

JO - Games and Economic Behavior

JF - Games and Economic Behavior

ER -

Learning the fundamentals in a stationary environment

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this