Saved in:
Bibliographic Details
Main Authors: Llewellyn, Mary, King, Ruth, Elvira, Víctor, Ross, Gordon
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.03395
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913637797462016
author Llewellyn, Mary
King, Ruth
Elvira, Víctor
Ross, Gordon
author_facet Llewellyn, Mary
King, Ruth
Elvira, Víctor
Ross, Gordon
contents We consider the challenge of estimating the model parameters and latent states of general state-space models within a Bayesian framework. We extend the commonly applied particle Gibbs framework by proposing an efficient particle generation scheme for the latent states. The approach efficiently samples particles using an approximate hidden Markov model (HMM) representation of the general state-space model via a deterministic grid on the state space. We refer to the approach as the grid particle Gibbs with ancestor sampling algorithm. We discuss several computational and practical aspects of the algorithm in detail and highlight further computational adjustments that improve the efficiency of the algorithm. The efficiency of the approach is investigated via challenging regime-switching models, including a post-COVID tourism demand model, and we demonstrate substantial computational gains compared to previous particle Gibbs with ancestor sampling methods.
format Preprint
id arxiv_https___arxiv_org_abs_2501_03395
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Grid Particle Gibbs with Ancestor Sampling for State-Space Models
Llewellyn, Mary
King, Ruth
Elvira, Víctor
Ross, Gordon
Computation
We consider the challenge of estimating the model parameters and latent states of general state-space models within a Bayesian framework. We extend the commonly applied particle Gibbs framework by proposing an efficient particle generation scheme for the latent states. The approach efficiently samples particles using an approximate hidden Markov model (HMM) representation of the general state-space model via a deterministic grid on the state space. We refer to the approach as the grid particle Gibbs with ancestor sampling algorithm. We discuss several computational and practical aspects of the algorithm in detail and highlight further computational adjustments that improve the efficiency of the algorithm. The efficiency of the approach is investigated via challenging regime-switching models, including a post-COVID tourism demand model, and we demonstrate substantial computational gains compared to previous particle Gibbs with ancestor sampling methods.
title Grid Particle Gibbs with Ancestor Sampling for State-Space Models
topic Computation
url https://arxiv.org/abs/2501.03395