Panel Data Models with Grouped Factor Structure Under Unknown Group Membership

Tomohiro Ando, Jushan Bai

研究成果: Article

21 引用 (Scopus)

抄録

This paper studies panel data models with unobserved group factor structures. The group membership of each unit and the number of groups are left unspecified. We estimate the model by minimizing the sum of least squared errors with a shrinkage penalty. The number of explanatory variables can be large. The regressions coefficients can be homogeneous or group specific. The consistency and asymptotic normality of the estimator are established. We also introduce new Cp-type criteria for selecting the number of groups, the numbers of group-specific common factors and relevant regressors. Monte Carlo results show that the proposed method works well. We apply the method to the study of US mutual fund returns and to the study of individual stock returns of the China mainland stock markets.

元の言語English
ページ(範囲)163-191
ページ数29
ジャーナルJournal of Applied Econometrics
31
発行部数1
DOI
出版物ステータスPublished - 2016 1 1

Fingerprint

group membership
Group
normality
stock market
penalty
Factors
Group membership
regression
China
Penalty
Shrinkage
Mutual funds
Common factors
Stock market
Stock returns
Estimator
Coefficients
Asymptotic normality
Mainland China

ASJC Scopus subject areas

  • Economics and Econometrics
  • Social Sciences (miscellaneous)

これを引用

Panel Data Models with Grouped Factor Structure Under Unknown Group Membership. / Ando, Tomohiro; Bai, Jushan.

:: Journal of Applied Econometrics, 巻 31, 番号 1, 01.01.2016, p. 163-191.

研究成果: Article

Ando, Tomohiro ; Bai, Jushan. / Panel Data Models with Grouped Factor Structure Under Unknown Group Membership. :: Journal of Applied Econometrics. 2016 ; 巻 31, 番号 1. pp. 163-191.
@article{712bd7c5e40644fab209ebe542c9cb7c,
title = "Panel Data Models with Grouped Factor Structure Under Unknown Group Membership",
abstract = "This paper studies panel data models with unobserved group factor structures. The group membership of each unit and the number of groups are left unspecified. We estimate the model by minimizing the sum of least squared errors with a shrinkage penalty. The number of explanatory variables can be large. The regressions coefficients can be homogeneous or group specific. The consistency and asymptotic normality of the estimator are established. We also introduce new Cp-type criteria for selecting the number of groups, the numbers of group-specific common factors and relevant regressors. Monte Carlo results show that the proposed method works well. We apply the method to the study of US mutual fund returns and to the study of individual stock returns of the China mainland stock markets.",
author = "Tomohiro Ando and Jushan Bai",
year = "2016",
month = "1",
day = "1",
doi = "10.1002/jae.2467",
language = "English",
volume = "31",
pages = "163--191",
journal = "Journal of Applied Econometrics",
issn = "0883-7252",
publisher = "John Wiley and Sons Ltd",
number = "1",

}

TY - JOUR

T1 - Panel Data Models with Grouped Factor Structure Under Unknown Group Membership

AU - Ando, Tomohiro

AU - Bai, Jushan

PY - 2016/1/1

Y1 - 2016/1/1

N2 - This paper studies panel data models with unobserved group factor structures. The group membership of each unit and the number of groups are left unspecified. We estimate the model by minimizing the sum of least squared errors with a shrinkage penalty. The number of explanatory variables can be large. The regressions coefficients can be homogeneous or group specific. The consistency and asymptotic normality of the estimator are established. We also introduce new Cp-type criteria for selecting the number of groups, the numbers of group-specific common factors and relevant regressors. Monte Carlo results show that the proposed method works well. We apply the method to the study of US mutual fund returns and to the study of individual stock returns of the China mainland stock markets.

AB - This paper studies panel data models with unobserved group factor structures. The group membership of each unit and the number of groups are left unspecified. We estimate the model by minimizing the sum of least squared errors with a shrinkage penalty. The number of explanatory variables can be large. The regressions coefficients can be homogeneous or group specific. The consistency and asymptotic normality of the estimator are established. We also introduce new Cp-type criteria for selecting the number of groups, the numbers of group-specific common factors and relevant regressors. Monte Carlo results show that the proposed method works well. We apply the method to the study of US mutual fund returns and to the study of individual stock returns of the China mainland stock markets.

UR - http://www.scopus.com/inward/record.url?scp=84957957179&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84957957179&partnerID=8YFLogxK

U2 - 10.1002/jae.2467

DO - 10.1002/jae.2467

M3 - Article

AN - SCOPUS:84957957179

VL - 31

SP - 163

EP - 191

JO - Journal of Applied Econometrics

JF - Journal of Applied Econometrics

SN - 0883-7252

IS - 1

ER -