Eigenvalue ratio test for the number of factors

Seung C. Ahn, Alex Horenstein

Research output: Contribution to journalArticle

137 Citations (Scopus)

Abstract

This paper proposes two new estimators for determining the number of factors (r) in static approximate factor models. We exploit the well-known fact that the r largest eigenvalues of the variance matrix of N response variables grow unboundedly as N increases, while the other eigenvalues remain bounded. The new estimators are obtained simply by maximizing the ratio of two adjacent eigenvalues. Our simulation results provide promising evidence for the two estimators.

Original languageEnglish (US)
Pages (from-to)1203-1227
Number of pages25
JournalEconometrica
Volume81
Issue number3
DOIs
StatePublished - May 1 2013

Fingerprint

Factors
Estimator
Eigenvalues
Simulation

Keywords

  • Approximate factor models
  • Eigenvalues
  • Number of factors

ASJC Scopus subject areas

  • Economics and Econometrics

Cite this

Eigenvalue ratio test for the number of factors. / Ahn, Seung C.; Horenstein, Alex.

In: Econometrica, Vol. 81, No. 3, 01.05.2013, p. 1203-1227.

Research output: Contribution to journalArticle

Ahn, Seung C. ; Horenstein, Alex. / Eigenvalue ratio test for the number of factors. In: Econometrica. 2013 ; Vol. 81, No. 3. pp. 1203-1227.
@article{f22bdaf6a3cc402397312bba130847d1,
title = "Eigenvalue ratio test for the number of factors",
abstract = "This paper proposes two new estimators for determining the number of factors (r) in static approximate factor models. We exploit the well-known fact that the r largest eigenvalues of the variance matrix of N response variables grow unboundedly as N increases, while the other eigenvalues remain bounded. The new estimators are obtained simply by maximizing the ratio of two adjacent eigenvalues. Our simulation results provide promising evidence for the two estimators.",
keywords = "Approximate factor models, Eigenvalues, Number of factors",
author = "Ahn, {Seung C.} and Alex Horenstein",
year = "2013",
month = "5",
day = "1",
doi = "10.3982/ECTA8968",
language = "English (US)",
volume = "81",
pages = "1203--1227",
journal = "Econometrica",
issn = "0012-9682",
publisher = "Wiley-Blackwell",
number = "3",

}

TY - JOUR

T1 - Eigenvalue ratio test for the number of factors

AU - Ahn, Seung C.

AU - Horenstein, Alex

PY - 2013/5/1

Y1 - 2013/5/1

N2 - This paper proposes two new estimators for determining the number of factors (r) in static approximate factor models. We exploit the well-known fact that the r largest eigenvalues of the variance matrix of N response variables grow unboundedly as N increases, while the other eigenvalues remain bounded. The new estimators are obtained simply by maximizing the ratio of two adjacent eigenvalues. Our simulation results provide promising evidence for the two estimators.

AB - This paper proposes two new estimators for determining the number of factors (r) in static approximate factor models. We exploit the well-known fact that the r largest eigenvalues of the variance matrix of N response variables grow unboundedly as N increases, while the other eigenvalues remain bounded. The new estimators are obtained simply by maximizing the ratio of two adjacent eigenvalues. Our simulation results provide promising evidence for the two estimators.

KW - Approximate factor models

KW - Eigenvalues

KW - Number of factors

UR - http://www.scopus.com/inward/record.url?scp=84877901545&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84877901545&partnerID=8YFLogxK

U2 - 10.3982/ECTA8968

DO - 10.3982/ECTA8968

M3 - Article

AN - SCOPUS:84877901545

VL - 81

SP - 1203

EP - 1227

JO - Econometrica

JF - Econometrica

SN - 0012-9682

IS - 3

ER -