Home > Research > Publications & Outputs > Modelling non-stationary extremes with applicat...
View graph of relations

Modelling non-stationary extremes with application to surface level ozone.

Research output: Contribution to journalJournal article

Published

Standard

Modelling non-stationary extremes with application to surface level ozone. / Eastoe, Emma F.; Tawn, Jonathan A.

In: Journal of the Royal Statistical Society: Series C (Applied Statistics), Vol. 58, No. 1, 02.2009, p. 25-45.

Research output: Contribution to journalJournal article

Harvard

Eastoe, EF & Tawn, JA 2009, 'Modelling non-stationary extremes with application to surface level ozone.', Journal of the Royal Statistical Society: Series C (Applied Statistics), vol. 58, no. 1, pp. 25-45. https://doi.org/10.1111/j.1467-9876.2008.00638.x

APA

Vancouver

Eastoe EF, Tawn JA. Modelling non-stationary extremes with application to surface level ozone. Journal of the Royal Statistical Society: Series C (Applied Statistics). 2009 Feb;58(1):25-45. https://doi.org/10.1111/j.1467-9876.2008.00638.x

Author

Eastoe, Emma F. ; Tawn, Jonathan A. / Modelling non-stationary extremes with application to surface level ozone. In: Journal of the Royal Statistical Society: Series C (Applied Statistics). 2009 ; Vol. 58, No. 1. pp. 25-45.

Bibtex

@article{e9bb87756ea443beb13b4d2a5d0d1ab0,
title = "Modelling non-stationary extremes with application to surface level ozone.",
abstract = "Statistical methods for modelling extremes of stationary sequences have received much attention. The most common method is to model the rate and size of exceedances of some high constant threshold; the size of exceedances is modelled by using a generalized Pareto distribution. Frequently, data sets display non-stationarity; this is especially common in environmental applications. The ozone data set that is presented here is an example of such a data set. Surface level ozone levels display complex seasonal patterns and trends due to the mechanisms that are involved in ozone formation. The standard methods of modelling the extremes of a non-stationary process focus on retaining a constant threshold but using covariate models in the rate and generalized Pareto distribution parameters. We suggest an alternative approach that uses preprocessing methods to model the non-stationarity in the body of the process and then uses standard methods to model the extremes of the preprocessed data. We illustrate both the standard and the preprocessing methods by using a simulation study and a study of the ozone data. We suggest that the preprocessing method gives a model that better incorporates the underlying mechanisms that generate the process, produces a simpler and more efficient fit and allows easier computation.",
keywords = "Generalized Pareto distribution • Non-stationary process • Ozone • Preprocessing • Return levels • Threshold exceedances",
author = "Eastoe, {Emma F.} and Tawn, {Jonathan A.}",
year = "2009",
month = feb
doi = "10.1111/j.1467-9876.2008.00638.x",
language = "English",
volume = "58",
pages = "25--45",
journal = "Journal of the Royal Statistical Society: Series C (Applied Statistics)",
issn = "0035-9254",
publisher = "Wiley-Blackwell",
number = "1",

}

RIS

TY - JOUR

T1 - Modelling non-stationary extremes with application to surface level ozone.

AU - Eastoe, Emma F.

AU - Tawn, Jonathan A.

PY - 2009/2

Y1 - 2009/2

N2 - Statistical methods for modelling extremes of stationary sequences have received much attention. The most common method is to model the rate and size of exceedances of some high constant threshold; the size of exceedances is modelled by using a generalized Pareto distribution. Frequently, data sets display non-stationarity; this is especially common in environmental applications. The ozone data set that is presented here is an example of such a data set. Surface level ozone levels display complex seasonal patterns and trends due to the mechanisms that are involved in ozone formation. The standard methods of modelling the extremes of a non-stationary process focus on retaining a constant threshold but using covariate models in the rate and generalized Pareto distribution parameters. We suggest an alternative approach that uses preprocessing methods to model the non-stationarity in the body of the process and then uses standard methods to model the extremes of the preprocessed data. We illustrate both the standard and the preprocessing methods by using a simulation study and a study of the ozone data. We suggest that the preprocessing method gives a model that better incorporates the underlying mechanisms that generate the process, produces a simpler and more efficient fit and allows easier computation.

AB - Statistical methods for modelling extremes of stationary sequences have received much attention. The most common method is to model the rate and size of exceedances of some high constant threshold; the size of exceedances is modelled by using a generalized Pareto distribution. Frequently, data sets display non-stationarity; this is especially common in environmental applications. The ozone data set that is presented here is an example of such a data set. Surface level ozone levels display complex seasonal patterns and trends due to the mechanisms that are involved in ozone formation. The standard methods of modelling the extremes of a non-stationary process focus on retaining a constant threshold but using covariate models in the rate and generalized Pareto distribution parameters. We suggest an alternative approach that uses preprocessing methods to model the non-stationarity in the body of the process and then uses standard methods to model the extremes of the preprocessed data. We illustrate both the standard and the preprocessing methods by using a simulation study and a study of the ozone data. We suggest that the preprocessing method gives a model that better incorporates the underlying mechanisms that generate the process, produces a simpler and more efficient fit and allows easier computation.

KW - Generalized Pareto distribution • Non-stationary process • Ozone • Preprocessing • Return levels • Threshold exceedances

U2 - 10.1111/j.1467-9876.2008.00638.x

DO - 10.1111/j.1467-9876.2008.00638.x

M3 - Journal article

VL - 58

SP - 25

EP - 45

JO - Journal of the Royal Statistical Society: Series C (Applied Statistics)

JF - Journal of the Royal Statistical Society: Series C (Applied Statistics)

SN - 0035-9254

IS - 1

ER -