On semiparametric testing of I(d) by FEXP models

Research output: Contribution to journalArticle

Abstract

To statistically test the assumption that a scalar-valued process is I(d), this article proposes a test statistic based on a broadband semiparametric method by use of fractional exponential (FEXP) models. The test is semiparametric in terms of flexibility in modeling spectral density. We establish the asymptotic behavior and report finite-sample performance by a Monte Carlo study.

Original languageEnglish
Pages (from-to)1637-1653
Number of pages17
JournalCommunications in Statistics - Theory and Methods
Volume42
Issue number9
DOIs
Publication statusPublished - 2013

Fingerprint

Exponential Model
Fractional
Semiparametric Methods
Testing
Spectral Density
Monte Carlo Study
Broadband
Test Statistic
Asymptotic Behavior
Flexibility
Scalar
Modeling

Keywords

  • Fractional exponential models
  • I(d) processes
  • Semiparametric testing

ASJC Scopus subject areas

  • Statistics and Probability

Cite this

On semiparametric testing of I(d) by FEXP models. / Narukawa, Masaki.

In: Communications in Statistics - Theory and Methods, Vol. 42, No. 9, 2013, p. 1637-1653.

Research output: Contribution to journalArticle

@article{12dd065f1b794127b92dc1de0ec27f6d,
title = "On semiparametric testing of I(d) by FEXP models",
abstract = "To statistically test the assumption that a scalar-valued process is I(d), this article proposes a test statistic based on a broadband semiparametric method by use of fractional exponential (FEXP) models. The test is semiparametric in terms of flexibility in modeling spectral density. We establish the asymptotic behavior and report finite-sample performance by a Monte Carlo study.",
keywords = "Fractional exponential models, I(d) processes, Semiparametric testing",
author = "Masaki Narukawa",
year = "2013",
doi = "10.1080/03610926.2011.594539",
language = "English",
volume = "42",
pages = "1637--1653",
journal = "Communications in Statistics - Theory and Methods",
issn = "0361-0926",
publisher = "Taylor and Francis Ltd.",
number = "9",

}

TY - JOUR

T1 - On semiparametric testing of I(d) by FEXP models

AU - Narukawa, Masaki

PY - 2013

Y1 - 2013

N2 - To statistically test the assumption that a scalar-valued process is I(d), this article proposes a test statistic based on a broadband semiparametric method by use of fractional exponential (FEXP) models. The test is semiparametric in terms of flexibility in modeling spectral density. We establish the asymptotic behavior and report finite-sample performance by a Monte Carlo study.

AB - To statistically test the assumption that a scalar-valued process is I(d), this article proposes a test statistic based on a broadband semiparametric method by use of fractional exponential (FEXP) models. The test is semiparametric in terms of flexibility in modeling spectral density. We establish the asymptotic behavior and report finite-sample performance by a Monte Carlo study.

KW - Fractional exponential models

KW - I(d) processes

KW - Semiparametric testing

UR - http://www.scopus.com/inward/record.url?scp=84877938417&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84877938417&partnerID=8YFLogxK

U2 - 10.1080/03610926.2011.594539

DO - 10.1080/03610926.2011.594539

M3 - Article

AN - SCOPUS:84877938417

VL - 42

SP - 1637

EP - 1653

JO - Communications in Statistics - Theory and Methods

JF - Communications in Statistics - Theory and Methods

SN - 0361-0926

IS - 9

ER -