Bayesian estimation of generalized partition of unity copulas

IF 0.6 Q4 STATISTICS & PROBABILITY

Dependence Modeling Pub Date : 2020-01-01 DOI:10.1515/DEMO-2020-0007

A. Masuhr, M. Trede

引用次数: 3

Abstract

Abstract This paper proposes a Bayesian estimation algorithm to estimate Generalized Partition of Unity Copulas (GPUC), a class of nonparametric copulas recently introduced by [18]. The first approach is a random walk Metropolis-Hastings (RW-MH) algorithm, the second one is a random blocking random walk Metropolis-Hastings algorithm (RBRW-MH). Both approaches are Markov chain Monte Carlo methods and can cope with ˛at priors. We carry out simulation studies to determine and compare the efficiency of the algorithms. We present an empirical illustration where GPUCs are used to nonparametrically describe the dependence of exchange rate changes of the crypto-currencies Bitcoin and Ethereum.

查看原文本刊更多论文

单位联结广义划分的贝叶斯估计

摘要本文提出了一种贝叶斯估计算法来估计单位Copula的广义划分（GPUC），这是[18]最近引入的一类非参数Copula。第一种方法是随机行走Metropolis-Hastings（RW-MH）算法，第二种方法是一种随机阻塞随机行走Mettopolis-Has廷s算法。这两种方法都是马尔可夫链蒙特卡罗方法，可以处理先验。我们进行了仿真研究，以确定和比较算法的效率。我们提供了一个实证说明，其中GPUC用于非框架地描述加密货币比特币和以太坊汇率变化的依赖性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Dependence Modeling STATISTICS & PROBABILITY-

CiteScore

1.00

自引率

0.00%

发文量

审稿时长

12 weeks

期刊介绍： The journal Dependence Modeling aims at providing a medium for exchanging results and ideas in the area of multivariate dependence modeling. It is an open access fully peer-reviewed journal providing the readers with free, instant, and permanent access to all content worldwide. Dependence Modeling is listed by Web of Science (Emerging Sources Citation Index), Scopus, MathSciNet and Zentralblatt Math. The journal presents different types of articles: -"Research Articles" on fundamental theoretical aspects, as well as on significant applications in science, engineering, economics, finance, insurance and other fields. -"Review Articles" which present the existing literature on the specific topic from new perspectives. -"Interview articles" limited to two papers per year, covering interviews with milestone personalities in the field of Dependence Modeling. The journal topics include (but are not limited to):　 -Copula methods -Multivariate distributions -Estimation and goodness-of-fit tests -Measures of association -Quantitative risk management -Risk measures and stochastic orders -Time series -Environmental sciences -Computational methods and software -Extreme-value theory -Limit laws -Mass Transportations