Tests for multinormality with applications to time series

Takeaki Kariya; Ruey S. Tsay; Nobuhiko Terui; Hong Li

doi:10.1080/03610929908832312

Tests for multinormality with applications to time series

Takeaki Kariya, Ruey S. Tsay, Nobuhiko Terui, Hong Li

Department of Business Economics

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

3 Citations (Scopus)

Abstract

Making use of a characterization of multivariate normality by Hermitian polynomials, we propose a multivariate normality test. The approach is then applied to time series analysis by constructing a test for Gaussianity of a stationary univariate series. Simulation study shows that the proposed test has reasonable power and outperforms other tests available in the literature when the innovation series of the time series is symmetric, but non-Gaussian.

Original language	English
Pages (from-to)	519-536
Number of pages	18
Journal	Communications in Statistics - Theory and Methods
Volume	28
Issue number	3-4
DOIs	https://doi.org/10.1080/03610929908832312
Publication status	Published - 1999

Keywords

Bispectrum test
Gaussianity
Hermitian polynomial
Kurtosis
Skewness
Test for multivariate normality

Access to Document

10.1080/03610929908832312

Cite this

@article{bd577252f9924dec958bdd2d251dc32a,

title = "Tests for multinormality with applications to time series",

abstract = "Making use of a characterization of multivariate normality by Hermitian polynomials, we propose a multivariate normality test. The approach is then applied to time series analysis by constructing a test for Gaussianity of a stationary univariate series. Simulation study shows that the proposed test has reasonable power and outperforms other tests available in the literature when the innovation series of the time series is symmetric, but non-Gaussian.",

keywords = "Bispectrum test, Gaussianity, Hermitian polynomial, Kurtosis, Skewness, Test for multivariate normality",

author = "Takeaki Kariya and Tsay, {Ruey S.} and Nobuhiko Terui and Hong Li",

note = "Funding Information: This research is supported in part by the Ministry of Education, Japan and by the National Science Foundation, USA. We would like to thank the associate editor and two anonymous referees for their useful comments.",

year = "1999",

doi = "10.1080/03610929908832312",

language = "English",

volume = "28",

pages = "519--536",

journal = "Communications in Statistics - Theory and Methods",

issn = "0361-0926",

publisher = "Taylor and Francis Ltd.",

number = "3-4",

}

TY - JOUR

T1 - Tests for multinormality with applications to time series

AU - Kariya, Takeaki

AU - Tsay, Ruey S.

AU - Terui, Nobuhiko

AU - Li, Hong

N1 - Funding Information: This research is supported in part by the Ministry of Education, Japan and by the National Science Foundation, USA. We would like to thank the associate editor and two anonymous referees for their useful comments.

PY - 1999

Y1 - 1999

N2 - Making use of a characterization of multivariate normality by Hermitian polynomials, we propose a multivariate normality test. The approach is then applied to time series analysis by constructing a test for Gaussianity of a stationary univariate series. Simulation study shows that the proposed test has reasonable power and outperforms other tests available in the literature when the innovation series of the time series is symmetric, but non-Gaussian.

AB - Making use of a characterization of multivariate normality by Hermitian polynomials, we propose a multivariate normality test. The approach is then applied to time series analysis by constructing a test for Gaussianity of a stationary univariate series. Simulation study shows that the proposed test has reasonable power and outperforms other tests available in the literature when the innovation series of the time series is symmetric, but non-Gaussian.

KW - Bispectrum test

KW - Gaussianity

KW - Hermitian polynomial

KW - Kurtosis

KW - Skewness

KW - Test for multivariate normality

UR - http://www.scopus.com/inward/record.url?scp=0013025398&partnerID=8YFLogxK

U2 - 10.1080/03610929908832312

DO - 10.1080/03610929908832312

M3 - Article

AN - SCOPUS:0013025398

SN - 0361-0926

VL - 28

SP - 519

EP - 536

JO - Communications in Statistics - Theory and Methods

JF - Communications in Statistics - Theory and Methods

IS - 3-4

ER -

Tests for multinormality with applications to time series

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this