No Cover Image

Journal article 1238 views

Automated threshold selection methods for extreme wave analysis

Paul Thompson, Yuzhi Cai Orcid Logo, Dominic Reeve Orcid Logo, Julian Stander

Coastal Engineering, Volume: 56, Issue: 10, Pages: 1013 - 1021

Swansea University Authors: Yuzhi Cai Orcid Logo, Dominic Reeve Orcid Logo

Full text not available from this repository: check for access using links below.

Check full text

DOI (Published version): 10.1016/j.coastaleng.2009.06.003

Abstract

The study of the extreme values of a variable such as wave height is very important in flood risk assessmentand coastal design. Often values above a sufficiently large threshold can be modelled using the GeneralizedPareto Distribution, the parameters of which are estimated using maximum likelihood....

Full description

Published in: Coastal Engineering
ISSN: 03783839
Published: 2009
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa11978
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2013-07-23T12:06:39Z
last_indexed 2019-10-11T19:09:15Z
id cronfa11978
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2019-10-11T15:26:26.3358892</datestamp><bib-version>v2</bib-version><id>11978</id><entry>2012-07-12</entry><title>Automated threshold selection methods for extreme wave analysis</title><swanseaauthors><author><sid>eff7b8626ab4cc6428eef52516fda7d6</sid><ORCID>0000-0003-3509-9787</ORCID><firstname>Yuzhi</firstname><surname>Cai</surname><name>Yuzhi Cai</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>3e76fcc2bb3cde4ddee2c8edfd2f0082</sid><ORCID>0000-0003-1293-4743</ORCID><firstname>Dominic</firstname><surname>Reeve</surname><name>Dominic Reeve</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2012-07-12</date><deptcode>BAF</deptcode><abstract>The study of the extreme values of a variable such as wave height is very important in flood risk assessmentand coastal design. Often values above a sufficiently large threshold can be modelled using the GeneralizedPareto Distribution, the parameters of which are estimated using maximum likelihood. There are severalpopular empirical techniques for choosing a suitable threshold, but these require the subjectiveinterpretation of plots by the user.We in this paper present a pragmatic automated, simple and computationally inexpensive threshold selectionmethod based on the distribution of the difference of parameter estimates when the threshold is changed,and apply it to a published rainfall and a new wave height data set. We assess the effect of the uncertaintyassociated with our threshold selection technique on return level estimation by using the bootstrapprocedure. We illustrate the effectiveness of our methodology by a simulation study and compare it with theapproach used in the JOINSEA software. In addition, we present an extension that allows the thresholdselected to depend on the value of a covariate such as the cosine of wave direction.</abstract><type>Journal Article</type><journal>Coastal Engineering</journal><volume>56</volume><journalNumber>10</journalNumber><paginationStart>1013</paginationStart><paginationEnd>1021</paginationEnd><publisher/><issnPrint>03783839</issnPrint><keywords>Bootstrap, Covariate dependent thresholds, Distribution with Generalized Pareto tail, Generalized Pareto Distribution, GPD,Return level confidence intervals</keywords><publishedDay>31</publishedDay><publishedMonth>10</publishedMonth><publishedYear>2009</publishedYear><publishedDate>2009-10-31</publishedDate><doi>10.1016/j.coastaleng.2009.06.003</doi><url/><notes/><college>COLLEGE NANME</college><department>Accounting and Finance</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>BAF</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2019-10-11T15:26:26.3358892</lastEdited><Created>2012-07-12T14:14:53.7968108</Created><path><level id="1">Faculty of Humanities and Social Sciences</level><level id="2">School of Management - Accounting and Finance</level></path><authors><author><firstname>Paul</firstname><surname>Thompson</surname><order>1</order></author><author><firstname>Yuzhi</firstname><surname>Cai</surname><orcid>0000-0003-3509-9787</orcid><order>2</order></author><author><firstname>Dominic</firstname><surname>Reeve</surname><orcid>0000-0003-1293-4743</orcid><order>3</order></author><author><firstname>Julian</firstname><surname>Stander</surname><order>4</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2019-10-11T15:26:26.3358892 v2 11978 2012-07-12 Automated threshold selection methods for extreme wave analysis eff7b8626ab4cc6428eef52516fda7d6 0000-0003-3509-9787 Yuzhi Cai Yuzhi Cai true false 3e76fcc2bb3cde4ddee2c8edfd2f0082 0000-0003-1293-4743 Dominic Reeve Dominic Reeve true false 2012-07-12 BAF The study of the extreme values of a variable such as wave height is very important in flood risk assessmentand coastal design. Often values above a sufficiently large threshold can be modelled using the GeneralizedPareto Distribution, the parameters of which are estimated using maximum likelihood. There are severalpopular empirical techniques for choosing a suitable threshold, but these require the subjectiveinterpretation of plots by the user.We in this paper present a pragmatic automated, simple and computationally inexpensive threshold selectionmethod based on the distribution of the difference of parameter estimates when the threshold is changed,and apply it to a published rainfall and a new wave height data set. We assess the effect of the uncertaintyassociated with our threshold selection technique on return level estimation by using the bootstrapprocedure. We illustrate the effectiveness of our methodology by a simulation study and compare it with theapproach used in the JOINSEA software. In addition, we present an extension that allows the thresholdselected to depend on the value of a covariate such as the cosine of wave direction. Journal Article Coastal Engineering 56 10 1013 1021 03783839 Bootstrap, Covariate dependent thresholds, Distribution with Generalized Pareto tail, Generalized Pareto Distribution, GPD,Return level confidence intervals 31 10 2009 2009-10-31 10.1016/j.coastaleng.2009.06.003 COLLEGE NANME Accounting and Finance COLLEGE CODE BAF Swansea University 2019-10-11T15:26:26.3358892 2012-07-12T14:14:53.7968108 Faculty of Humanities and Social Sciences School of Management - Accounting and Finance Paul Thompson 1 Yuzhi Cai 0000-0003-3509-9787 2 Dominic Reeve 0000-0003-1293-4743 3 Julian Stander 4
title Automated threshold selection methods for extreme wave analysis
spellingShingle Automated threshold selection methods for extreme wave analysis
Yuzhi Cai
Dominic Reeve
title_short Automated threshold selection methods for extreme wave analysis
title_full Automated threshold selection methods for extreme wave analysis
title_fullStr Automated threshold selection methods for extreme wave analysis
title_full_unstemmed Automated threshold selection methods for extreme wave analysis
title_sort Automated threshold selection methods for extreme wave analysis
author_id_str_mv eff7b8626ab4cc6428eef52516fda7d6
3e76fcc2bb3cde4ddee2c8edfd2f0082
author_id_fullname_str_mv eff7b8626ab4cc6428eef52516fda7d6_***_Yuzhi Cai
3e76fcc2bb3cde4ddee2c8edfd2f0082_***_Dominic Reeve
author Yuzhi Cai
Dominic Reeve
author2 Paul Thompson
Yuzhi Cai
Dominic Reeve
Julian Stander
format Journal article
container_title Coastal Engineering
container_volume 56
container_issue 10
container_start_page 1013
publishDate 2009
institution Swansea University
issn 03783839
doi_str_mv 10.1016/j.coastaleng.2009.06.003
college_str Faculty of Humanities and Social Sciences
hierarchytype
hierarchy_top_id facultyofhumanitiesandsocialsciences
hierarchy_top_title Faculty of Humanities and Social Sciences
hierarchy_parent_id facultyofhumanitiesandsocialsciences
hierarchy_parent_title Faculty of Humanities and Social Sciences
department_str School of Management - Accounting and Finance{{{_:::_}}}Faculty of Humanities and Social Sciences{{{_:::_}}}School of Management - Accounting and Finance
document_store_str 0
active_str 0
description The study of the extreme values of a variable such as wave height is very important in flood risk assessmentand coastal design. Often values above a sufficiently large threshold can be modelled using the GeneralizedPareto Distribution, the parameters of which are estimated using maximum likelihood. There are severalpopular empirical techniques for choosing a suitable threshold, but these require the subjectiveinterpretation of plots by the user.We in this paper present a pragmatic automated, simple and computationally inexpensive threshold selectionmethod based on the distribution of the difference of parameter estimates when the threshold is changed,and apply it to a published rainfall and a new wave height data set. We assess the effect of the uncertaintyassociated with our threshold selection technique on return level estimation by using the bootstrapprocedure. We illustrate the effectiveness of our methodology by a simulation study and compare it with theapproach used in the JOINSEA software. In addition, we present an extension that allows the thresholdselected to depend on the value of a covariate such as the cosine of wave direction.
published_date 2009-10-31T03:13:52Z
_version_ 1763750165042167808
score 10.999161

Similar Items