King's College London

Research portal

Objective priors for the number of degrees of freedom of a multivariate distribution and the t-copula

Research output: Contribution to journalArticle

Original languageEnglish
Pages (from-to)197-219
Number of pages23
JournalCOMPUTATIONAL STATISTICS AND DATA ANALYSIS
Volume124
Early online date27 Mar 2018
DOIs
Publication statusPublished - Aug 2018

Documents

King's Authors

Abstract

An objective Bayesian approach to estimate the number of degrees of freedom for the multivariate distribution and for the -copula, when the parameter is considered discrete, is proposed. Inference on this parameter has been problematic for the multivariate and, for the absence of any method, for the -copula. An objective criterion based on loss functions which allows to overcome the issue of defining objective probabilities directly is employed. The support of the prior for is truncated, which derives from the property of both the multivariate and the -copula of convergence to normality for a sufficiently large number of degrees of freedom. The performance of the priors is tested on simulated scenarios 1and on real data: daily logarithmic returns of IBM and of the Center for Research in Security Prices Database.

Download statistics

No data available

View graph of relations

© 2018 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454