文章基本信息

标题：FITTING EXTREME VALUE COPULAS WITH UNIMODAL CONVEX POLYNOMIAL REGRESSION USING BERNSTEIN POLYNOMIALS
本地全文：下载
作者：Danielle Gonçalves de Oliveira PRADO ; Lucas Monteiro CHAVES ; Devanil Jaques de SOUZA 等
期刊名称：Revista Brasileira de Biometria
印刷版ISSN：0102-0811
电子版ISSN：1983-0823
出版年度：2022
卷号：40
期号：2
DOI：10.28951/bjb.v40i2.548
语种：English
出版社：Universidade Federal de Lavras
摘要：Bernstein polynomials are suitable for performing shape-constrained regressions, in particular, for unimodal convex regression. The Pickands function is convex and unimodal, being a fundamental element in the theory of extreme value copulas. The purpose of this article is to explain in details the use of Bernstein polynomials in the estimation of Pickands function and to establish a new test of significance for extreme value copulas.