Construction of prediction intervals for Palmer Drought Severity Index using bootstrap

Ufuk Beyaztas, Bugrayhan Bickici Arikan*, Beste Hamiye Beyaztas, Ercan Kahya

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

25 Citations (Scopus)

Abstract

In this study, we propose an approach based on the residual-based bootstrap method to obtain valid prediction intervals using monthly, short-term (three-months) and mid-term (six-months) drought observations. The effects of North Atlantic and Arctic Oscillation indexes on the constructed prediction intervals are also examined. Performance of the proposed approach is evaluated for the Palmer Drought Severity Index (PDSI) obtained from Konya closed basin located in Central Anatolia, Turkey. The finite sample properties of the proposed method are further illustrated by an extensive simulation study. Our results revealed that the proposed approach is capable of producing valid prediction intervals for future PDSI values.

Original languageEnglish
Pages (from-to)461-470
Number of pages10
JournalJournal of Hydrology
Volume559
DOIs
Publication statusPublished - Apr 2018

Bibliographical note

Publisher Copyright:
© 2018 Elsevier B.V.

Funding

We thank two anonymous referees for valuable suggestions and comments, which helped us improve the manuscrip significantly. We would like to acknowledge the support of TUBITAK (Scientific and Technological Research Council of Turkey) for financial support. The authors wish to thank to MGM (Turkish State Meteorological Service) authorities for providing data.

FundersFunder number
TUBITAK
Türkiye Bilimsel ve Teknolojik Araştirma Kurumu

    Keywords

    • Bootstrap
    • Drought
    • Konya basin
    • PDSI
    • Prediction

    Fingerprint

    Dive into the research topics of 'Construction of prediction intervals for Palmer Drought Severity Index using bootstrap'. Together they form a unique fingerprint.

    Cite this