Skip to main content

Sequential Monte Carlo methods for mixtures with normalized random measures with independent increments priors

Griffin, Jim E. (2015) Sequential Monte Carlo methods for mixtures with normalized random measures with independent increments priors. Statistics and Computing, 27 (1). pp. 131-145. ISSN 0960-3174. (doi:10.1007/s11222-015-9612-3) (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided) (KAR id:63600)

The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided. (Contact us about this Publication)
Official URL
https://doi.org/10.1007/s11222-015-9612-3

Abstract

Normalized random measures with independent increments are a general, tractable class of nonparametric prior. This paper describes sequential Monte Carlo methods for both conjugate and non-conjugate nonparametric mixture models with these priors. A simulation study is used to compare the efficiency of the different algorithms for density estimation and comparisons made with Markov chain Monte Carlo methods. The SMC methods are further illustrated by applications to dynamically fitting a nonparametric stochastic volatility model and to estimation of the marginal likelihood in a goodness-of-fit testing example.

Item Type: Article
DOI/Identification number: 10.1007/s11222-015-9612-3
Uncontrolled keywords: Bayesian nonparametrics; Dirichlet process; Normalized generalized gamma process; Nonparametric stochastic volatility; Slice sampling; Particle Gibbs sampling
Divisions: Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Mathematics, Statistics and Actuarial Science
Depositing User: Jim Griffin
Date Deposited: 27 Sep 2017 14:09 UTC
Last Modified: 16 Feb 2021 13:48 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/63600 (The current URI for this page, for reference purposes)
Griffin, Jim E.: https://orcid.org/0000-0002-4828-7368
  • Depositors only (login required):