A nonparametric assessment of properties of space-time covariance functions

Bo Li, Marc G. Genton, Michael Sherman

Research output: Contribution to journalArticle

Abstract

We propose a unified framework for testing various assumptions commonly made for covariance functions of stationary spatio-temporal random fields. The methodology is based on the asymptotic normality of space-time covariance estimators. We focus on tests for full symmetry and separability in this article, but our framework naturally covers testing for isotropy and Taylor"s hypothesis. Our test successfully detects the asymmetric and nonseparable features in two sets of wind speed data. We perform simulation experiments to evaluate our test and conclude that our method is reliable and powerful for assessing common assumptions on space-time covariance functions.

Original languageEnglish (US)
Pages (from-to)736-744
Number of pages9
JournalJournal of the American Statistical Association
Volume102
Issue number478
DOIs
StatePublished - Jun 1 2007

Fingerprint

Covariance Function
Space-time
Testing
Nonseparable
Isotropy
Wind Speed
Separability
Asymptotic Normality
Random Field
Simulation Experiment
Cover
Estimator
Symmetry
Methodology
Evaluate
Framework

Keywords

  • Asymptotic normality
  • Covariance
  • Full symmetry
  • Random field
  • Separability
  • Stationarity

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

A nonparametric assessment of properties of space-time covariance functions. / Li, Bo; Genton, Marc G.; Sherman, Michael.

In: Journal of the American Statistical Association, Vol. 102, No. 478, 01.06.2007, p. 736-744.

Research output: Contribution to journalArticle

Li, Bo ; Genton, Marc G. ; Sherman, Michael. / A nonparametric assessment of properties of space-time covariance functions. In: Journal of the American Statistical Association. 2007 ; Vol. 102, No. 478. pp. 736-744.
@article{d1d7cf3bfb974062a0ae8b5569338d69,
title = "A nonparametric assessment of properties of space-time covariance functions",
abstract = "We propose a unified framework for testing various assumptions commonly made for covariance functions of stationary spatio-temporal random fields. The methodology is based on the asymptotic normality of space-time covariance estimators. We focus on tests for full symmetry and separability in this article, but our framework naturally covers testing for isotropy and Taylor{"}s hypothesis. Our test successfully detects the asymmetric and nonseparable features in two sets of wind speed data. We perform simulation experiments to evaluate our test and conclude that our method is reliable and powerful for assessing common assumptions on space-time covariance functions.",
keywords = "Asymptotic normality, Covariance, Full symmetry, Random field, Separability, Stationarity",
author = "Bo Li and Genton, {Marc G.} and Michael Sherman",
year = "2007",
month = "6",
day = "1",
doi = "10.1198/016214507000000202",
language = "English (US)",
volume = "102",
pages = "736--744",
journal = "Journal of the American Statistical Association",
issn = "0162-1459",
publisher = "Taylor & Francis",
number = "478",

}

TY - JOUR

T1 - A nonparametric assessment of properties of space-time covariance functions

AU - Li, Bo

AU - Genton, Marc G.

AU - Sherman, Michael

PY - 2007/6/1

Y1 - 2007/6/1

N2 - We propose a unified framework for testing various assumptions commonly made for covariance functions of stationary spatio-temporal random fields. The methodology is based on the asymptotic normality of space-time covariance estimators. We focus on tests for full symmetry and separability in this article, but our framework naturally covers testing for isotropy and Taylor"s hypothesis. Our test successfully detects the asymmetric and nonseparable features in two sets of wind speed data. We perform simulation experiments to evaluate our test and conclude that our method is reliable and powerful for assessing common assumptions on space-time covariance functions.

AB - We propose a unified framework for testing various assumptions commonly made for covariance functions of stationary spatio-temporal random fields. The methodology is based on the asymptotic normality of space-time covariance estimators. We focus on tests for full symmetry and separability in this article, but our framework naturally covers testing for isotropy and Taylor"s hypothesis. Our test successfully detects the asymmetric and nonseparable features in two sets of wind speed data. We perform simulation experiments to evaluate our test and conclude that our method is reliable and powerful for assessing common assumptions on space-time covariance functions.

KW - Asymptotic normality

KW - Covariance

KW - Full symmetry

KW - Random field

KW - Separability

KW - Stationarity

UR - http://www.scopus.com/inward/record.url?scp=34250783936&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34250783936&partnerID=8YFLogxK

U2 - 10.1198/016214507000000202

DO - 10.1198/016214507000000202

M3 - Article

VL - 102

SP - 736

EP - 744

JO - Journal of the American Statistical Association

JF - Journal of the American Statistical Association

SN - 0162-1459

IS - 478

ER -