Modelling multiple time series via common factors

Jiazhu Pan, Qiwei Yao

Research output: Contribution to journalArticle

48 Citations (Scopus)

Abstract

We propose a new method for estimating common factors of multiple time series. One distinctive feature of the new approach is that it is applicable to some nonstationary time series. The unobservable (nonstationary) factors are identified via expanding the white noise space step by step; therefore solving a high-dimensional optimization problem by several low-dimensional subproblems. Asymptotic properties of the estimation were investigated. The proposed methodology was illustrated with both simulated and real data sets.
LanguageEnglish
Pages365-379
Number of pages15
JournalBiometrika
Volume95
Issue number2
Early online date1 Sep 2007
DOIs
Publication statusPublished - 2008

Fingerprint

Multiple Time Series
Non-stationary Time Series
Common factor
White noise
Asymptotic Properties
Time series
time series analysis
High-dimensional
Optimization Problem
system optimization
Modeling
Non-stationary time series
Asymptotic properties
Optimization problem
Factors
Common factors
Multiple time series
methodology
Datasets

Keywords

  • factor models
  • cross-correlation functions
  • dimension reduction
  • multivariate time series
  • non stationarity
  • portmanteau tests
  • white noise

Cite this

Pan, Jiazhu ; Yao, Qiwei. / Modelling multiple time series via common factors. In: Biometrika. 2008 ; Vol. 95, No. 2. pp. 365-379.
@article{2585a06918a74ba68f2f998962b9a327,
title = "Modelling multiple time series via common factors",
abstract = "We propose a new method for estimating common factors of multiple time series. One distinctive feature of the new approach is that it is applicable to some nonstationary time series. The unobservable (nonstationary) factors are identified via expanding the white noise space step by step; therefore solving a high-dimensional optimization problem by several low-dimensional subproblems. Asymptotic properties of the estimation were investigated. The proposed methodology was illustrated with both simulated and real data sets.",
keywords = "factor models, cross-correlation functions, dimension reduction, multivariate time series, non stationarity, portmanteau tests, white noise",
author = "Jiazhu Pan and Qiwei Yao",
year = "2008",
doi = "10.1093/biomet/asn009",
language = "English",
volume = "95",
pages = "365--379",
journal = "Biometrika",
issn = "1464-3510",
number = "2",

}

Modelling multiple time series via common factors. / Pan, Jiazhu; Yao, Qiwei.

In: Biometrika, Vol. 95, No. 2, 2008, p. 365-379.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Modelling multiple time series via common factors

AU - Pan, Jiazhu

AU - Yao, Qiwei

PY - 2008

Y1 - 2008

N2 - We propose a new method for estimating common factors of multiple time series. One distinctive feature of the new approach is that it is applicable to some nonstationary time series. The unobservable (nonstationary) factors are identified via expanding the white noise space step by step; therefore solving a high-dimensional optimization problem by several low-dimensional subproblems. Asymptotic properties of the estimation were investigated. The proposed methodology was illustrated with both simulated and real data sets.

AB - We propose a new method for estimating common factors of multiple time series. One distinctive feature of the new approach is that it is applicable to some nonstationary time series. The unobservable (nonstationary) factors are identified via expanding the white noise space step by step; therefore solving a high-dimensional optimization problem by several low-dimensional subproblems. Asymptotic properties of the estimation were investigated. The proposed methodology was illustrated with both simulated and real data sets.

KW - factor models

KW - cross-correlation functions

KW - dimension reduction

KW - multivariate time series

KW - non stationarity

KW - portmanteau tests

KW - white noise

U2 - 10.1093/biomet/asn009

DO - 10.1093/biomet/asn009

M3 - Article

VL - 95

SP - 365

EP - 379

JO - Biometrika

T2 - Biometrika

JF - Biometrika

SN - 1464-3510

IS - 2

ER -