Robust estimation in a nonlinear cointegration model

Jia Chen; Degui Li; Lixin Zhang

doi:10.1016/j.jmva.2009.09.004

Robust estimation in a nonlinear cointegration model

Jia Chen, Degui Li^*, Lixin Zhang

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

This paper considers the nonparametric M-estimator in a nonlinear cointegration type model. The local time density argument, which was developed by Phillips and Park (1998) [6] and Wang and Phillips (2009)[9], is applied to establish the asymptotic theory for the nonparametric M-estimator. The weak consistency and the asymptotic distribution of the proposed estimator are established under mild conditions. Meanwhile, the asymptotic distribution of the local least squares estimator and the local least absolute distance estimator can be obtained as applications of our main results. Furthermore, an iterated procedure for obtaining the nonparametric M-estimator and a cross-validation bandwidth selection method are discussed, and some numerical examples are provided to show that the proposed methods perform well in the finite sample case.

Original language	English
Pages (from-to)	706-717
Number of pages	12
Journal	Journal of Multivariate Analysis
Volume	101
Issue number	3
DOIs	https://doi.org/10.1016/j.jmva.2009.09.004
Publication status	Published - Mar 2010

Bibliographical note

Keywords

UNIT ROOTS
Nonparametric M-estimator
Local time density
ASYMPTOTIC THEORY
INITIAL CONDITION
LOCAL M-ESTIMATOR
Cointegration model
REGRESSION
NONPARAMETRIC-ESTIMATION
TIME-SERIES DATA

Access to Document

10.1016/j.jmva.2009.09.004

Cite this

@article{8f2fc00b1bc641328d897f1792cc00e6,

title = "Robust estimation in a nonlinear cointegration model",

abstract = "This paper considers the nonparametric M-estimator in a nonlinear cointegration type model. The local time density argument, which was developed by Phillips and Park (1998) [6] and Wang and Phillips (2009)[9], is applied to establish the asymptotic theory for the nonparametric M-estimator. The weak consistency and the asymptotic distribution of the proposed estimator are established under mild conditions. Meanwhile, the asymptotic distribution of the local least squares estimator and the local least absolute distance estimator can be obtained as applications of our main results. Furthermore, an iterated procedure for obtaining the nonparametric M-estimator and a cross-validation bandwidth selection method are discussed, and some numerical examples are provided to show that the proposed methods perform well in the finite sample case. ",

keywords = "UNIT ROOTS, Nonparametric M-estimator, Local time density, ASYMPTOTIC THEORY, INITIAL CONDITION, LOCAL M-ESTIMATOR, Cointegration model, REGRESSION, NONPARAMETRIC-ESTIMATION, TIME-SERIES DATA",

author = "Jia Chen and Degui Li and Lixin Zhang",

year = "2010",

month = mar,

doi = "10.1016/j.jmva.2009.09.004",

language = "English",

volume = "101",

pages = "706--717",

journal = "Journal of Multivariate Analysis",

issn = "0047-259X",

publisher = "Academic Press",

number = "3",

}

TY - JOUR

T1 - Robust estimation in a nonlinear cointegration model

AU - Chen, Jia

AU - Li, Degui

AU - Zhang, Lixin

PY - 2010/3

Y1 - 2010/3

N2 - This paper considers the nonparametric M-estimator in a nonlinear cointegration type model. The local time density argument, which was developed by Phillips and Park (1998) [6] and Wang and Phillips (2009)[9], is applied to establish the asymptotic theory for the nonparametric M-estimator. The weak consistency and the asymptotic distribution of the proposed estimator are established under mild conditions. Meanwhile, the asymptotic distribution of the local least squares estimator and the local least absolute distance estimator can be obtained as applications of our main results. Furthermore, an iterated procedure for obtaining the nonparametric M-estimator and a cross-validation bandwidth selection method are discussed, and some numerical examples are provided to show that the proposed methods perform well in the finite sample case.

AB - This paper considers the nonparametric M-estimator in a nonlinear cointegration type model. The local time density argument, which was developed by Phillips and Park (1998) [6] and Wang and Phillips (2009)[9], is applied to establish the asymptotic theory for the nonparametric M-estimator. The weak consistency and the asymptotic distribution of the proposed estimator are established under mild conditions. Meanwhile, the asymptotic distribution of the local least squares estimator and the local least absolute distance estimator can be obtained as applications of our main results. Furthermore, an iterated procedure for obtaining the nonparametric M-estimator and a cross-validation bandwidth selection method are discussed, and some numerical examples are provided to show that the proposed methods perform well in the finite sample case.

KW - UNIT ROOTS

KW - Nonparametric M-estimator

KW - Local time density

KW - ASYMPTOTIC THEORY

KW - INITIAL CONDITION

KW - LOCAL M-ESTIMATOR

KW - Cointegration model

KW - REGRESSION

KW - NONPARAMETRIC-ESTIMATION

KW - TIME-SERIES DATA

UR - http://www.scopus.com/inward/record.url?scp=72549118948&partnerID=8YFLogxK

U2 - 10.1016/j.jmva.2009.09.004

DO - 10.1016/j.jmva.2009.09.004

M3 - Article

SN - 0047-259X

VL - 101

SP - 706

EP - 717

JO - Journal of Multivariate Analysis

JF - Journal of Multivariate Analysis

IS - 3

ER -

Robust estimation in a nonlinear cointegration model

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Cite this