Testing for two-regime threshold cointegration in vector error-correction models

Bruce E. Hansen, Byeongseon Seo

Research output: Contribution to journalArticle

390 Citations (Scopus)

Abstract

This paper examines a two-regime vector error-correction model with a single cointegrating vector and a threshold effect in the error-correction term. We propose a relatively simple algorithm to obtain maximum likelihood estimation of the complete threshold cointegration model for the bivariate case. We propose a SupLM test for the presence of a threshold. We derive the null asymptotic distribution, show how to simulate asymptotic critical values, and present a bootstrap approximation. We investigate the performance of the test using Monte Carlo simulation, and find that the test works quite well. Applying our methods to the term structure model of interest rates, we find strong evidence for a threshold effect.

Original languageEnglish
Pages (from-to)293-318
Number of pages26
JournalJournal of Econometrics
Volume110
Issue number2
DOIs
Publication statusPublished - 2002 Oct 1
Externally publishedYes

Fingerprint

Error Correction Model
Cointegration
Error correction
Testing
Maximum likelihood estimation
Model structures
Term Structure
Null Distribution
Error Correction
Interest Rates
Maximum Likelihood Estimation
Bootstrap
Asymptotic distribution
Critical value
Monte Carlo Simulation
Vector error correction model
Threshold cointegration
Term
Approximation
Model

Keywords

  • Bootstrap
  • Identification
  • Non-linear
  • Non-stationary
  • Term structure

ASJC Scopus subject areas

  • Economics and Econometrics
  • Finance
  • Statistics and Probability

Cite this

Testing for two-regime threshold cointegration in vector error-correction models. / Hansen, Bruce E.; Seo, Byeongseon.

In: Journal of Econometrics, Vol. 110, No. 2, 01.10.2002, p. 293-318.

Research output: Contribution to journalArticle

@article{e10b89b999d04618a7af90dd58dda753,
title = "Testing for two-regime threshold cointegration in vector error-correction models",
abstract = "This paper examines a two-regime vector error-correction model with a single cointegrating vector and a threshold effect in the error-correction term. We propose a relatively simple algorithm to obtain maximum likelihood estimation of the complete threshold cointegration model for the bivariate case. We propose a SupLM test for the presence of a threshold. We derive the null asymptotic distribution, show how to simulate asymptotic critical values, and present a bootstrap approximation. We investigate the performance of the test using Monte Carlo simulation, and find that the test works quite well. Applying our methods to the term structure model of interest rates, we find strong evidence for a threshold effect.",
keywords = "Bootstrap, Identification, Non-linear, Non-stationary, Term structure",
author = "Hansen, {Bruce E.} and Byeongseon Seo",
year = "2002",
month = "10",
day = "1",
doi = "10.1016/S0304-4076(02)00097-0",
language = "English",
volume = "110",
pages = "293--318",
journal = "Journal of Econometrics",
issn = "0304-4076",
publisher = "Elsevier BV",
number = "2",

}

TY - JOUR

T1 - Testing for two-regime threshold cointegration in vector error-correction models

AU - Hansen, Bruce E.

AU - Seo, Byeongseon

PY - 2002/10/1

Y1 - 2002/10/1

N2 - This paper examines a two-regime vector error-correction model with a single cointegrating vector and a threshold effect in the error-correction term. We propose a relatively simple algorithm to obtain maximum likelihood estimation of the complete threshold cointegration model for the bivariate case. We propose a SupLM test for the presence of a threshold. We derive the null asymptotic distribution, show how to simulate asymptotic critical values, and present a bootstrap approximation. We investigate the performance of the test using Monte Carlo simulation, and find that the test works quite well. Applying our methods to the term structure model of interest rates, we find strong evidence for a threshold effect.

AB - This paper examines a two-regime vector error-correction model with a single cointegrating vector and a threshold effect in the error-correction term. We propose a relatively simple algorithm to obtain maximum likelihood estimation of the complete threshold cointegration model for the bivariate case. We propose a SupLM test for the presence of a threshold. We derive the null asymptotic distribution, show how to simulate asymptotic critical values, and present a bootstrap approximation. We investigate the performance of the test using Monte Carlo simulation, and find that the test works quite well. Applying our methods to the term structure model of interest rates, we find strong evidence for a threshold effect.

KW - Bootstrap

KW - Identification

KW - Non-linear

KW - Non-stationary

KW - Term structure

UR - http://www.scopus.com/inward/record.url?scp=0037836631&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037836631&partnerID=8YFLogxK

U2 - 10.1016/S0304-4076(02)00097-0

DO - 10.1016/S0304-4076(02)00097-0

M3 - Article

AN - SCOPUS:0037836631

VL - 110

SP - 293

EP - 318

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

IS - 2

ER -