Behaviour of Dickey-Fuller unit-root tests under trend misspecification

Tae Hwan Kim, Stephen Leybourne, Paul Newbold

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

We analyse the case where a unit-root test is based on a Dickey-Fuller regression the only deterministic term of which is a fixed intercept. Suppose, however, as could well be the case, that the actual data-generating process includes a broken linear trend. It is shown theoretically, and verified empirically, that under the I(1) null and I(0) alternative hypotheses the Dickey-Fuller test can display a wide range of different characteristics depending on the nature and location of the break.

Original languageEnglish
Pages (from-to)755-764
Number of pages10
JournalJournal of Time Series Analysis
Volume25
Issue number5
DOIs
Publication statusPublished - 2004 Sep 1

Fingerprint

Dickey-Fuller Test
Linear Trend
Unit Root Tests
Misspecification
Intercept
Null
Regression
Alternatives
Term
Range of data
Trends
Dickey-Fuller test
Unit root tests
Data generating process

All Science Journal Classification (ASJC) codes

  • Applied Mathematics
  • Statistics and Probability

Cite this

Kim, Tae Hwan ; Leybourne, Stephen ; Newbold, Paul. / Behaviour of Dickey-Fuller unit-root tests under trend misspecification. In: Journal of Time Series Analysis. 2004 ; Vol. 25, No. 5. pp. 755-764.
@article{70243274d1a543e7abb106b8f728f2be,
title = "Behaviour of Dickey-Fuller unit-root tests under trend misspecification",
abstract = "We analyse the case where a unit-root test is based on a Dickey-Fuller regression the only deterministic term of which is a fixed intercept. Suppose, however, as could well be the case, that the actual data-generating process includes a broken linear trend. It is shown theoretically, and verified empirically, that under the I(1) null and I(0) alternative hypotheses the Dickey-Fuller test can display a wide range of different characteristics depending on the nature and location of the break.",
author = "Kim, {Tae Hwan} and Stephen Leybourne and Paul Newbold",
year = "2004",
month = "9",
day = "1",
doi = "10.1111/j.1467-9892.2004.02000.x",
language = "English",
volume = "25",
pages = "755--764",
journal = "Journal of Time Series Analysis",
issn = "0143-9782",
publisher = "Wiley-Blackwell",
number = "5",

}

Behaviour of Dickey-Fuller unit-root tests under trend misspecification. / Kim, Tae Hwan; Leybourne, Stephen; Newbold, Paul.

In: Journal of Time Series Analysis, Vol. 25, No. 5, 01.09.2004, p. 755-764.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Behaviour of Dickey-Fuller unit-root tests under trend misspecification

AU - Kim, Tae Hwan

AU - Leybourne, Stephen

AU - Newbold, Paul

PY - 2004/9/1

Y1 - 2004/9/1

N2 - We analyse the case where a unit-root test is based on a Dickey-Fuller regression the only deterministic term of which is a fixed intercept. Suppose, however, as could well be the case, that the actual data-generating process includes a broken linear trend. It is shown theoretically, and verified empirically, that under the I(1) null and I(0) alternative hypotheses the Dickey-Fuller test can display a wide range of different characteristics depending on the nature and location of the break.

AB - We analyse the case where a unit-root test is based on a Dickey-Fuller regression the only deterministic term of which is a fixed intercept. Suppose, however, as could well be the case, that the actual data-generating process includes a broken linear trend. It is shown theoretically, and verified empirically, that under the I(1) null and I(0) alternative hypotheses the Dickey-Fuller test can display a wide range of different characteristics depending on the nature and location of the break.

UR - http://www.scopus.com/inward/record.url?scp=3943067680&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=3943067680&partnerID=8YFLogxK

U2 - 10.1111/j.1467-9892.2004.02000.x

DO - 10.1111/j.1467-9892.2004.02000.x

M3 - Article

VL - 25

SP - 755

EP - 764

JO - Journal of Time Series Analysis

JF - Journal of Time Series Analysis

SN - 0143-9782

IS - 5

ER -