Convergence of adaptive learning and expectational stability: The case of multiple rational-expectations equilibria

Research output: Journal contributionsJournal articlesResearchpeer-review

Standard

Convergence of adaptive learning and expectational stability: The case of multiple rational-expectations equilibria. / Heinemann, Maik.
In: Macroeconomic Dynamics, Vol. 4, No. 3, 01.09.2000, p. 263-288.

Research output: Journal contributionsJournal articlesResearchpeer-review

Harvard

APA

Vancouver

Bibtex

@article{4a2bc881a3fa4b2fbcaa5f3b651cf07a,
title = "Convergence of adaptive learning and expectational stability: The case of multiple rational-expectations equilibria",
abstract = "This paper analyzes the relationship between the expectational stability of rational expectations solutions and the possible convergence of adaptive learning processes. Both concepts are used as selection criteria in the case of multiple rational expectations solutions. Results obtained using recursive least squares lead to the conjecture that there exists a general one-to-one correspondence between these two selection criteria. On thebasis of a simple linear model and a stochastic gradient algorithm as an alternative learning procedure, it is demonstrated that such a conjecture would be incorrect: There are cases in which stochastic gradient learning converges to rational expectations solutions that are not expectationally stable.",
keywords = "Economics, Expectational stability, Learning, Multiple equilibria",
author = "Maik Heinemann",
year = "2000",
month = sep,
day = "1",
doi = "10.1017/S1365100500016011",
language = "English",
volume = "4",
pages = "263--288",
journal = "Macroeconomic Dynamics",
issn = "1365-1005",
publisher = "Cambridge University Press",
number = "3",

}

RIS

TY - JOUR

T1 - Convergence of adaptive learning and expectational stability

T2 - The case of multiple rational-expectations equilibria

AU - Heinemann, Maik

PY - 2000/9/1

Y1 - 2000/9/1

N2 - This paper analyzes the relationship between the expectational stability of rational expectations solutions and the possible convergence of adaptive learning processes. Both concepts are used as selection criteria in the case of multiple rational expectations solutions. Results obtained using recursive least squares lead to the conjecture that there exists a general one-to-one correspondence between these two selection criteria. On thebasis of a simple linear model and a stochastic gradient algorithm as an alternative learning procedure, it is demonstrated that such a conjecture would be incorrect: There are cases in which stochastic gradient learning converges to rational expectations solutions that are not expectationally stable.

AB - This paper analyzes the relationship between the expectational stability of rational expectations solutions and the possible convergence of adaptive learning processes. Both concepts are used as selection criteria in the case of multiple rational expectations solutions. Results obtained using recursive least squares lead to the conjecture that there exists a general one-to-one correspondence between these two selection criteria. On thebasis of a simple linear model and a stochastic gradient algorithm as an alternative learning procedure, it is demonstrated that such a conjecture would be incorrect: There are cases in which stochastic gradient learning converges to rational expectations solutions that are not expectationally stable.

KW - Economics

KW - Expectational stability

KW - Learning

KW - Multiple equilibria

UR - http://www.scopus.com/inward/record.url?scp=0034398636&partnerID=8YFLogxK

U2 - 10.1017/S1365100500016011

DO - 10.1017/S1365100500016011

M3 - Journal articles

VL - 4

SP - 263

EP - 288

JO - Macroeconomic Dynamics

JF - Macroeconomic Dynamics

SN - 1365-1005

IS - 3

ER -