Semiparametric Whittle estimation of a cyclical long-memory time series based on generalised exponential models

Research output: Contribution to journalArticle

Abstract

This paper considers a semiparametric estimation of the memory parameter in a cyclical long-memory time series, which exhibits a strong dependence on cyclical behaviour, using the Whittle likelihood based on generalised exponential (GEXP) models. The proposed estimation is included in the so-called broadband or global method and uses information from the spectral density at all frequencies. We establish the consistency and the asymptotic normality of the estimated memory parameter for a linear process and thus do not require Gaussianity. A simulation study conducted using Monte Carlo experiments shows that the proposed estimation works well compared to other existing semiparametric estimations. Moreover, we provide an empirical application of the proposed estimation, applying it to the growth rate of Japan's industrial production index and detecting its cyclical persistence.

Original languageEnglish
Pages (from-to)272-295
Number of pages24
JournalJournal of Nonparametric Statistics
Volume28
Issue number2
DOIs
Publication statusPublished - Apr 2 2016

Fingerprint

Exponential Model
Long Memory
Semiparametric Estimation
Time series
Whittle Likelihood
Linear Process
Monte Carlo Experiment
Spectral Density
Asymptotic Normality
Japan
Persistence
Broadband
Simulation Study
Long memory
Semiparametric estimation

Keywords

  • cyclical behaviour
  • exponential models
  • long memory
  • semiparametric estimation

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

@article{c9a2fb83f0d44a5ba8fd4fb5611eec12,
title = "Semiparametric Whittle estimation of a cyclical long-memory time series based on generalised exponential models",
abstract = "This paper considers a semiparametric estimation of the memory parameter in a cyclical long-memory time series, which exhibits a strong dependence on cyclical behaviour, using the Whittle likelihood based on generalised exponential (GEXP) models. The proposed estimation is included in the so-called broadband or global method and uses information from the spectral density at all frequencies. We establish the consistency and the asymptotic normality of the estimated memory parameter for a linear process and thus do not require Gaussianity. A simulation study conducted using Monte Carlo experiments shows that the proposed estimation works well compared to other existing semiparametric estimations. Moreover, we provide an empirical application of the proposed estimation, applying it to the growth rate of Japan's industrial production index and detecting its cyclical persistence.",
keywords = "cyclical behaviour, exponential models, long memory, semiparametric estimation",
author = "Masaki Narukawa",
year = "2016",
month = "4",
day = "2",
doi = "10.1080/10485252.2016.1163350",
language = "English",
volume = "28",
pages = "272--295",
journal = "Journal of Nonparametric Statistics",
issn = "1048-5252",
publisher = "Taylor and Francis Ltd.",
number = "2",

}

TY - JOUR

T1 - Semiparametric Whittle estimation of a cyclical long-memory time series based on generalised exponential models

AU - Narukawa, Masaki

PY - 2016/4/2

Y1 - 2016/4/2

N2 - This paper considers a semiparametric estimation of the memory parameter in a cyclical long-memory time series, which exhibits a strong dependence on cyclical behaviour, using the Whittle likelihood based on generalised exponential (GEXP) models. The proposed estimation is included in the so-called broadband or global method and uses information from the spectral density at all frequencies. We establish the consistency and the asymptotic normality of the estimated memory parameter for a linear process and thus do not require Gaussianity. A simulation study conducted using Monte Carlo experiments shows that the proposed estimation works well compared to other existing semiparametric estimations. Moreover, we provide an empirical application of the proposed estimation, applying it to the growth rate of Japan's industrial production index and detecting its cyclical persistence.

AB - This paper considers a semiparametric estimation of the memory parameter in a cyclical long-memory time series, which exhibits a strong dependence on cyclical behaviour, using the Whittle likelihood based on generalised exponential (GEXP) models. The proposed estimation is included in the so-called broadband or global method and uses information from the spectral density at all frequencies. We establish the consistency and the asymptotic normality of the estimated memory parameter for a linear process and thus do not require Gaussianity. A simulation study conducted using Monte Carlo experiments shows that the proposed estimation works well compared to other existing semiparametric estimations. Moreover, we provide an empirical application of the proposed estimation, applying it to the growth rate of Japan's industrial production index and detecting its cyclical persistence.

KW - cyclical behaviour

KW - exponential models

KW - long memory

KW - semiparametric estimation

UR - http://www.scopus.com/inward/record.url?scp=84964012329&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964012329&partnerID=8YFLogxK

U2 - 10.1080/10485252.2016.1163350

DO - 10.1080/10485252.2016.1163350

M3 - Article

AN - SCOPUS:84964012329

VL - 28

SP - 272

EP - 295

JO - Journal of Nonparametric Statistics

JF - Journal of Nonparametric Statistics

SN - 1048-5252

IS - 2

ER -