Approximate p-values of certain tests involving hypotheses about multiple breaks

Alastair Hall, Nikolaos Sakkas

Research output: Contribution to journalArticle

Abstract

We provide formulae for calculating approximate p-values for the non-standard asymptotic null distributions of a variety of tests used for detecting multiple structural change in a wide range of models. Our approximations are based on simulated quantiles obtained from 100,000 replications, and the latter are more accurate than the quantiles reported in the literature by a factor of 10,000 replications. The p-value response surfaces are approximated using a parametric method proposed by Hansen (1997) and their use is illustrated with an example. Using our p-value response surfaces, it is shown that the use of Bai and Perron’s (2003b) response surfaces for the critical values of these tests can lead to misleading inferences, and thus should be used with extreme caution.
LanguageEnglish
Pages53-67
JournalJournal of Econometric Methods
Volume2
Issue number1
DOIs
StatusPublished - Mar 2013

Fingerprint

quantiles
inference
approximation

Cite this

Approximate p-values of certain tests involving hypotheses about multiple breaks. / Hall, Alastair; Sakkas, Nikolaos.

In: Journal of Econometric Methods, Vol. 2, No. 1, 03.2013, p. 53-67.

Research output: Contribution to journalArticle

@article{154a956e1a3f42c1b987720e3966fce9,
title = "Approximate p-values of certain tests involving hypotheses about multiple breaks",
abstract = "We provide formulae for calculating approximate p-values for the non-standard asymptotic null distributions of a variety of tests used for detecting multiple structural change in a wide range of models. Our approximations are based on simulated quantiles obtained from 100,000 replications, and the latter are more accurate than the quantiles reported in the literature by a factor of 10,000 replications. The p-value response surfaces are approximated using a parametric method proposed by Hansen (1997) and their use is illustrated with an example. Using our p-value response surfaces, it is shown that the use of Bai and Perron’s (2003b) response surfaces for the critical values of these tests can lead to misleading inferences, and thus should be used with extreme caution.",
author = "Alastair Hall and Nikolaos Sakkas",
year = "2013",
month = "3",
doi = "10.1515/jem-2012-0014",
language = "English",
volume = "2",
pages = "53--67",
journal = "Journal of Econometric Methods",
issn = "2156-6674",
number = "1",

}

TY - JOUR

T1 - Approximate p-values of certain tests involving hypotheses about multiple breaks

AU - Hall,Alastair

AU - Sakkas,Nikolaos

PY - 2013/3

Y1 - 2013/3

N2 - We provide formulae for calculating approximate p-values for the non-standard asymptotic null distributions of a variety of tests used for detecting multiple structural change in a wide range of models. Our approximations are based on simulated quantiles obtained from 100,000 replications, and the latter are more accurate than the quantiles reported in the literature by a factor of 10,000 replications. The p-value response surfaces are approximated using a parametric method proposed by Hansen (1997) and their use is illustrated with an example. Using our p-value response surfaces, it is shown that the use of Bai and Perron’s (2003b) response surfaces for the critical values of these tests can lead to misleading inferences, and thus should be used with extreme caution.

AB - We provide formulae for calculating approximate p-values for the non-standard asymptotic null distributions of a variety of tests used for detecting multiple structural change in a wide range of models. Our approximations are based on simulated quantiles obtained from 100,000 replications, and the latter are more accurate than the quantiles reported in the literature by a factor of 10,000 replications. The p-value response surfaces are approximated using a parametric method proposed by Hansen (1997) and their use is illustrated with an example. Using our p-value response surfaces, it is shown that the use of Bai and Perron’s (2003b) response surfaces for the critical values of these tests can lead to misleading inferences, and thus should be used with extreme caution.

UR - http://dx.doi.org/10.1515/jem-2012-0014

U2 - 10.1515/jem-2012-0014

DO - 10.1515/jem-2012-0014

M3 - Article

VL - 2

SP - 53

EP - 67

JO - Journal of Econometric Methods

T2 - Journal of Econometric Methods

JF - Journal of Econometric Methods

SN - 2156-6674

IS - 1

ER -