Spurious break

Luis C. Nunes; Chung Ming Kuan; Paul Newbold

doi:10.1017/S0266466600009713

Spurious break

Luis C. Nunes, Chung Ming Kuan, Paul Newbold

NOVA School of Business and Economics (NOVA SBE)

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

57 Citations (Scopus)

Abstract

A quasi-maximum likelihood estimator of the break date is analyzed. Consistency of the estimator is demonstrated under very general conditions, provided that the data-generating process is not integrated. However, the asymptotic distribution of the estimator is quite different for time series that are integrated of order one. In that case, when there is no break, the analyst can be spuriously led to the estimation of a break near the middle of the time series.

Original language	English
Pages (from-to)	736-749
Number of pages	14
Journal	Econometric Theory
Volume	11
Issue number	4
DOIs	https://doi.org/10.1017/S0266466600009713
Publication status	Published - 1995

Access to Document

10.1017/S0266466600009713

Cite this

@article{32e9f08e11284b059ed449811cc4fab2,

title = "Spurious break",

abstract = "A quasi-maximum likelihood estimator of the break date is analyzed. Consistency of the estimator is demonstrated under very general conditions, provided that the data-generating process is not integrated. However, the asymptotic distribution of the estimator is quite different for time series that are integrated of order one. In that case, when there is no break, the analyst can be spuriously led to the estimation of a break near the middle of the time series.",

author = "Nunes, {Luis C.} and Kuan, {Chung Ming} and Paul Newbold",

year = "1995",

doi = "10.1017/S0266466600009713",

language = "English",

volume = "11",

pages = "736--749",

journal = "Econometric Theory",

issn = "0266-4666",

publisher = "Cambridge University Press",

number = "4",

}

TY - JOUR

T1 - Spurious break

AU - Nunes, Luis C.

AU - Kuan, Chung Ming

AU - Newbold, Paul

PY - 1995

Y1 - 1995

N2 - A quasi-maximum likelihood estimator of the break date is analyzed. Consistency of the estimator is demonstrated under very general conditions, provided that the data-generating process is not integrated. However, the asymptotic distribution of the estimator is quite different for time series that are integrated of order one. In that case, when there is no break, the analyst can be spuriously led to the estimation of a break near the middle of the time series.

AB - A quasi-maximum likelihood estimator of the break date is analyzed. Consistency of the estimator is demonstrated under very general conditions, provided that the data-generating process is not integrated. However, the asymptotic distribution of the estimator is quite different for time series that are integrated of order one. In that case, when there is no break, the analyst can be spuriously led to the estimation of a break near the middle of the time series.

UR - http://www.scopus.com/inward/record.url?scp=21844513196&partnerID=8YFLogxK

U2 - 10.1017/S0266466600009713

DO - 10.1017/S0266466600009713

M3 - Article

AN - SCOPUS:21844513196

SN - 0266-4666

VL - 11

SP - 736

EP - 749

JO - Econometric Theory

JF - Econometric Theory

IS - 4

ER -

Spurious break

Abstract

Access to Document

Other files and links

Fingerprint

Cite this