Number of the records: 1  

Coverage probability of bootstrap confidence intervals in heavy-tailed frequency models, with application to precipitation data

  1. 1.
    SYSNO ASEP0350698
    Document TypeJ - Journal Article
    R&D Document TypeJournal Article
    Subsidiary JČlánek ve WOS
    TitleCoverage probability of bootstrap confidence intervals in heavy-tailed frequency models, with application to precipitation data
    Author(s) Kyselý, Jan (UFA-U) RID
    Source TitleTheoretical and Applied Climatology - ISSN 0177-798X
    Roč. 101, 3-4 (2010), s. 345-361
    Number of pages17 s.
    Languageeng - English
    CountryAT - Austria
    Keywordsbootstrap ; extreme value analysis ; confidence intervals ; heavy-tailed distributions ; precipitation amounts
    Subject RIVDG - Athmosphere Sciences, Meteorology
    R&D ProjectsKJB300420801 GA AV ČR - Academy of Sciences of the Czech Republic (AV ČR)
    CEZAV0Z30420517 - UFA-U, BC-A (2005-2011)
    UT WOS000280578900009
    DOI10.1007/s00704-009-0190-1
    AnnotationThe paper compares coverage probabilities of confidence intervals of high quantiles (5-yr to 200-yr return values) constructed by the nonparametric and parametric bootstrap in frequency analysis of heavy-tailed data, typical for maxima of precipitation amounts. The simulation experiments are based on a wide range of models used for precipitation extremes (Generalized Extreme Value, Generalized Pareto, Generalized Logistic, and mixed distributions). We show that both bootstrap methods underestimate the width of the confidence intervals but that the parametric bootstrap is clearly superior to the nonparametric one.
    WorkplaceInstitute of Atmospheric Physics
    ContactKateřina Adamovičová, adamovicova@ufa.cas.cz, Tel.: 272 016 012 ; Kateřina Potužníková, kaca@ufa.cas.cz, Tel.: 272 016 019
    Year of Publishing2011