The Gibbs sampler with particle efficient importance sampling for state-space models
From MaRDI portal
Abstract: We consider Particle Gibbs (PG) as a tool for Bayesian analysis of non-linear non-Gaussian state-space models. PG is a Monte Carlo (MC) approximation of the standard Gibbs procedure which uses sequential MC (SMC) importance sampling inside the Gibbs procedure to update the latent and potentially high-dimensional state trajectories. We propose to combine PG with a generic and easily implementable SMC approach known as Particle Efficient Importance Sampling (PEIS). By using SMC importance sampling densities which are approximately fully globally adapted to the targeted density of the states, PEIS can substantially improve the mixing and the efficiency of the PG draws from the posterior of the states and the parameters relative to existing PG implementations. The efficiency gains achieved by PEIS are illustrated in PG applications to a univariate stochastic volatility model for asset returns, a non-Gaussian nonlinear local-level model for interest rates, and a multivariate stochastic volatility model for the realized covariance matrix of asset returns.
Recommendations
Cites work
- scientific article; zbMATH DE number 5919872 (Why is no real title available?)
- scientific article; zbMATH DE number 4062374 (Why is no real title available?)
- A theory of the term structure of interest rates
- Analysis of financial time series
- Bayesian interference based only on simulated likelihood particle filter analysis of dynamic economic models
- Black's Model of Interest Rates as Options, Eigenfunction Expansions and Japanese Interest Rates
- Econometric Analysis of Realized Covariation: High Frequency Based Covariance, Regression, and Correlation in Financial Economics
- Efficient high-dimensional importance sampling
- Filtering via Simulation: Auxiliary Particle Filters
- Lookahead strategies for sequential Monte Carlo
- On some properties of Markov chain Monte Carlo simulation methods based on the particle filter
- Particle Gibbs with ancestor sampling
- Particle Markov Chain Monte Carlo Methods
- Particle Markov chain Monte Carlo for efficient numerical simulation
- Particle efficient importance sampling
- Statistical methods in finance
- Stochastic Volatility: Likelihood Inference and Comparison with ARCH Models
- The Collapsed Gibbs Sampler in Bayesian Computations with Applications to a Gene Regulation Problem
- The conditional autoregressive Wishart model for multivariate stock market volatility
Cited in
(14)- On disturbance state-space models and the particle marginal Metropolis-Hastings sampler
- Particle Gibbs with ancestor sampling for stochastic volatility models with: heavy tails, in mean effects, leverage, serial dependence and structural breaks
- On particle Gibbs sampling
- Particle Gibbs with ancestor sampling
- Log-density gradient covariance and automatic metric tensors for Riemann manifold Monte Carlo methods
- Bayesian estimation of state-space models using the Metropolis-Hastings algorithm within Gibbs sampling.
- Leverage, Asymmetry, and Heavy Tails in the High-Dimensional Factor Stochastic Volatility Model
- Particle efficient importance sampling
- Spatiotemporal blocking of the bouncy particle sampler for efficient inference in state-space models
- Gibbs sampler by sampling-importance-resampling
- Connecting the Dots: Numerical Randomized Hamiltonian Monte Carlo with State-Dependent Event Rates
- Importance Sampling-Based Transport Map Hamiltonian Monte Carlo for Bayesian Hierarchical Models
- Modeling realized covariance measures with heterogeneous liquidity: a generalized matrix-variate Wishart state-space model
- Modified Cholesky Riemann manifold Hamiltonian Monte Carlo: exploiting sparsity for fast sampling of high-dimensional targets
This page was built for publication: The Gibbs sampler with particle efficient importance sampling for state-space models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5860963)
