|
Activity Number:
|
491
|
|
Type:
|
Invited
|
|
Date/Time:
|
Thursday, August 10, 2006 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
ENAR
|
| Abstract - #305133 |
|
Title:
|
Nonparametric Estimation of Copulas via Mixtures
|
|
Author(s):
|
Peter Hoff*+
|
|
Companies:
|
University of Washington
|
|
Address:
|
, Seattle, WA, 98195-4322,
|
|
Keywords:
|
extreme points ; multivariate estimation ; mixture model
|
|
Abstract:
|
Every multivariate probability distribution can be decomposed into its univariate marginal densities and a copula, a joint density on the square with uniform marginals. In this talk we discuss mixture models for nonparametric estimation of copulas. In particular, we present a Dirichlet process mixture prior based on Bernstein polynomials whose support is the entire space of multivariate copulas. Estimation proceeds via a straightforward MCMC algorithm. Example analyses of mixed discrete and continuous data are presented, and model simplification strategies are discussed.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2006 program |
