LASSO estimation of threshold autoregressive models

Ngai Hang Chan; Chun Yip Yau; Rong-Mao Zhang

doi:10.1016/j.jeconom.2015.03.023

LASSO estimation of threshold autoregressive models

Ngai Hang Chan
, Chun Yip Yau
, Rong-Mao Zhang^*

^*Corresponding author for this work

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

43 Citations (Scopus)

Abstract

This paper develops a novel approach for estimating a threshold autoregressive (TAR) model with multiple-regimes and establishes its large sample properties. By reframing the problem in a regression variable selection context, a least absolute shrinkage and selection operator (LASSO) procedure is proposed to estimate a TAR model with an unknown number of thresholds, where the computation can be performed efficiently. It is further shown that the number and the location of the thresholds can be consistently estimated. A near optimal convergence rate of the threshold parameters is also established. Simulation studies are conducted to assess the performance in finite samples. The results are illustrated with an application to the quarterly US real GNP data over the period 1947-2009.

Original language	English
Pages (from-to)	285-296
Journal	Journal of Econometrics
Volume	189
Issue number	2
DOIs	https://doi.org/10.1016/j.jeconom.2015.03.023
Publication status	Published - 1 Dec 2015
Externally published	Yes

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Research Keywords

Group lasso
Information criterion
Least angle regression (LARS)
Multiple regimes

Access Output

10.1016/j.jeconom.2015.03.023

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{7b2ad6ca84e14953b12f5161a5ce8d92,

title = "LASSO estimation of threshold autoregressive models",

abstract = "This paper develops a novel approach for estimating a threshold autoregressive (TAR) model with multiple-regimes and establishes its large sample properties. By reframing the problem in a regression variable selection context, a least absolute shrinkage and selection operator (LASSO) procedure is proposed to estimate a TAR model with an unknown number of thresholds, where the computation can be performed efficiently. It is further shown that the number and the location of the thresholds can be consistently estimated. A near optimal convergence rate of the threshold parameters is also established. Simulation studies are conducted to assess the performance in finite samples. The results are illustrated with an application to the quarterly US real GNP data over the period 1947-2009.",

keywords = "Group lasso, Information criterion, Least angle regression (LARS), Multiple regimes",

author = "Chan, \{Ngai Hang\} and Yau, \{Chun Yip\} and Rong-Mao Zhang",

note = "Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected]. ",

year = "2015",

month = dec,

day = "1",

doi = "10.1016/j.jeconom.2015.03.023",

language = "English",

volume = "189",

pages = "285--296",

journal = "Journal of Econometrics",

issn = "0304-4076",

publisher = "Elsevier B.V.",

number = "2",

}

TY - JOUR

T1 - LASSO estimation of threshold autoregressive models

AU - Chan, Ngai Hang

AU - Yau, Chun Yip

AU - Zhang, Rong-Mao

N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

PY - 2015/12/1

Y1 - 2015/12/1

N2 - This paper develops a novel approach for estimating a threshold autoregressive (TAR) model with multiple-regimes and establishes its large sample properties. By reframing the problem in a regression variable selection context, a least absolute shrinkage and selection operator (LASSO) procedure is proposed to estimate a TAR model with an unknown number of thresholds, where the computation can be performed efficiently. It is further shown that the number and the location of the thresholds can be consistently estimated. A near optimal convergence rate of the threshold parameters is also established. Simulation studies are conducted to assess the performance in finite samples. The results are illustrated with an application to the quarterly US real GNP data over the period 1947-2009.

AB - This paper develops a novel approach for estimating a threshold autoregressive (TAR) model with multiple-regimes and establishes its large sample properties. By reframing the problem in a regression variable selection context, a least absolute shrinkage and selection operator (LASSO) procedure is proposed to estimate a TAR model with an unknown number of thresholds, where the computation can be performed efficiently. It is further shown that the number and the location of the thresholds can be consistently estimated. A near optimal convergence rate of the threshold parameters is also established. Simulation studies are conducted to assess the performance in finite samples. The results are illustrated with an application to the quarterly US real GNP data over the period 1947-2009.

KW - Group lasso

KW - Information criterion

KW - Least angle regression (LARS)

KW - Multiple regimes

UR - https://www.scopus.com/pages/publications/84945457749

UR - https://www.scopus.com/pages/publications/84945457749#tab=impact

U2 - 10.1016/j.jeconom.2015.03.023

DO - 10.1016/j.jeconom.2015.03.023

M3 - RGC 21 - Publication in refereed journal

SN - 0304-4076

VL - 189

SP - 285

EP - 296

JO - Journal of Econometrics

JF - Journal of Econometrics

IS - 2

ER -

LASSO estimation of threshold autoregressive models

Abstract

Bibliographical note

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this