Markov-switching models with endogenous explanatory variables

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

The maximum likelihood estimation of a Markov-switching regression model based on the Hamilton filter is not valid in the presence of endogenous explanatory variables. However, we show that there exists an appropriate transformation of the model that allows us to directly employ the Hamilton filter. The transformed model explicitly allows for a vector of bias correction terms as additional regressors, and the new disturbance term is uncorrelated with all the regressors in the transformed model. Within this framework, a quasi maximum likelihood estimation procedure is presented. A procedure to test for endogeneity based on the Wald statistic or the likelihood ratio statistic is also presented.

Original languageEnglish
Pages (from-to)127-136
Number of pages10
JournalJournal of Econometrics
Volume122
Issue number1
DOIs
Publication statusPublished - 2004 Sep 1

Fingerprint

Markov Switching Model
Maximum Likelihood Estimation
Maximum likelihood estimation
Wald Statistic
Filter
Endogeneity
Quasi-maximum Likelihood
Markov Switching
Bias Correction
Likelihood Ratio Statistic
Statistics
Term
Regression Model
Disturbance
Model
Valid
Model-based
Markov switching model

Keywords

  • Bias correction
  • Endogeneity
  • Forward-looking monetary policy rule
  • Hausman-Wu test
  • Markov switching

ASJC Scopus subject areas

  • Economics and Econometrics
  • Finance
  • Statistics and Probability

Cite this

Markov-switching models with endogenous explanatory variables. / Kim, Chang-Jin.

In: Journal of Econometrics, Vol. 122, No. 1, 01.09.2004, p. 127-136.

Research output: Contribution to journalArticle

@article{abb287c09aa14615a7270d8a7de5c456,
title = "Markov-switching models with endogenous explanatory variables",
abstract = "The maximum likelihood estimation of a Markov-switching regression model based on the Hamilton filter is not valid in the presence of endogenous explanatory variables. However, we show that there exists an appropriate transformation of the model that allows us to directly employ the Hamilton filter. The transformed model explicitly allows for a vector of bias correction terms as additional regressors, and the new disturbance term is uncorrelated with all the regressors in the transformed model. Within this framework, a quasi maximum likelihood estimation procedure is presented. A procedure to test for endogeneity based on the Wald statistic or the likelihood ratio statistic is also presented.",
keywords = "Bias correction, Endogeneity, Forward-looking monetary policy rule, Hausman-Wu test, Markov switching",
author = "Chang-Jin Kim",
year = "2004",
month = "9",
day = "1",
doi = "10.1016/j.jeconom.2003.10.021",
language = "English",
volume = "122",
pages = "127--136",
journal = "Journal of Econometrics",
issn = "0304-4076",
publisher = "Elsevier BV",
number = "1",

}

TY - JOUR

T1 - Markov-switching models with endogenous explanatory variables

AU - Kim, Chang-Jin

PY - 2004/9/1

Y1 - 2004/9/1

N2 - The maximum likelihood estimation of a Markov-switching regression model based on the Hamilton filter is not valid in the presence of endogenous explanatory variables. However, we show that there exists an appropriate transformation of the model that allows us to directly employ the Hamilton filter. The transformed model explicitly allows for a vector of bias correction terms as additional regressors, and the new disturbance term is uncorrelated with all the regressors in the transformed model. Within this framework, a quasi maximum likelihood estimation procedure is presented. A procedure to test for endogeneity based on the Wald statistic or the likelihood ratio statistic is also presented.

AB - The maximum likelihood estimation of a Markov-switching regression model based on the Hamilton filter is not valid in the presence of endogenous explanatory variables. However, we show that there exists an appropriate transformation of the model that allows us to directly employ the Hamilton filter. The transformed model explicitly allows for a vector of bias correction terms as additional regressors, and the new disturbance term is uncorrelated with all the regressors in the transformed model. Within this framework, a quasi maximum likelihood estimation procedure is presented. A procedure to test for endogeneity based on the Wald statistic or the likelihood ratio statistic is also presented.

KW - Bias correction

KW - Endogeneity

KW - Forward-looking monetary policy rule

KW - Hausman-Wu test

KW - Markov switching

UR - http://www.scopus.com/inward/record.url?scp=3042771244&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=3042771244&partnerID=8YFLogxK

U2 - 10.1016/j.jeconom.2003.10.021

DO - 10.1016/j.jeconom.2003.10.021

M3 - Article

AN - SCOPUS:3042771244

VL - 122

SP - 127

EP - 136

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

IS - 1

ER -