Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

A Generalized Bivariate Copula for Flood Analysis in Peninsular Malaysia

Version 1 : Received: 6 August 2018 / Approved: 6 August 2018 / Online: 6 August 2018 (11:39:25 CEST)

How to cite: Kamaruzaman, I.F.; Wan Zin, W.Z.; Mohd Ariff, N. A Generalized Bivariate Copula for Flood Analysis in Peninsular Malaysia. Preprints 2018, 2018080118. https://doi.org/10.20944/preprints201808.0118.v1 Kamaruzaman, I.F.; Wan Zin, W.Z.; Mohd Ariff, N. A Generalized Bivariate Copula for Flood Analysis in Peninsular Malaysia. Preprints 2018, 2018080118. https://doi.org/10.20944/preprints201808.0118.v1

Abstract

This study generalized the best copula to characterize the joint probability distribution between rainfall severity and duration in Peninsular Malaysia using two dimensional copulas. Specifically, to construct copulas, Inference Function for Margins (IFM) and Canonical Maximum Likelihood (CML) methods were specially exploited. For the purpose of achieving copula fitting, the derived rainfall variables by making use of the Standardized Precipitation Index (SPI) were fitted into several distributions. Five copulas, namely Gaussian, Clayton, Frank, Joe and Gumbel were put to the tests to establish the best data fitted copula. The tests produced acknowledged and satisfactory results of copula fitting for rainfall severity and duration. Surveying the Akaike Information Criterion (AIC) and the Bayesian Information Criterion (BIC), only three copulas produced a better fit for parametric and semi parametric approaches. Finally, two consistency tests were conducted and the results had shown that Frank Copula produced consistent results.

Keywords

Archimedean Copula; Elliptical Copula; Multivariate Distribution; Hydrology

Subject

Computer Science and Mathematics, Probability and Statistics

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.

Leave a public comment
Send a private comment to the author(s)
* All users must log in before leaving a comment
Views 0
Downloads 0
Comments 0
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.