Particle efficient importance sampling
From MaRDI portal
Publication:894644
DOI10.1016/J.JECONOM.2015.03.047zbMATH Open1419.62247arXiv1309.6745OpenAlexW1534371749MaRDI QIDQ894644FDOQ894644
Publication date: 2 December 2015
Published in: Journal of Econometrics (Search for Journal in Brave)
Abstract: The efficient importance sampling (EIS) method is a general principle for the numerical evaluation of high-dimensional integrals that uses the sequential structure of target integrands to build variance minimising importance samplers. Despite a number of successful applications in high dimensions, it is well known that importance sampling strategies are subject to an exponential growth in variance as the dimension of the integration increases. We solve this problem by recognising that the EIS framework has an offline sequential Monte Carlo interpretation. The particle EIS method is based on non-standard resampling weights that take into account the look-ahead construction of the importance sampler. We apply the method for a range of univariate and bivariate stochastic volatility specifications. We also develop a new application of the EIS approach to state space models with Student's t state innovations. Our results show that the particle EIS method strongly outperforms both the standard EIS method and particle filters for likelihood evaluation in high dimensions. Moreover, the ratio between the variances of the particle EIS and particle filter methods remains stable as the time series dimension increases. We illustrate the efficiency of the method for Bayesian inference using the particle marginal Metropolis-Hastings and importance sampling squared algorithms.
Full work available at URL: https://arxiv.org/abs/1309.6745
Recommendations
- Efficient high-dimensional importance sampling
- Improving MCMC, using efficient importance sampling
- Efficient importance sampling in mixture frameworks
- Classical and Bayesian Analysis of Univariate and Multivariate Stochastic Volatility Models
- The Gibbs sampler with particle efficient importance sampling for state-space models
sequential Monte CarloBayesian inferencestochastic volatilityparticle filtersparticle marginal Metropolis-Hastings
Bayesian inference (62F15) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Monte Carlo methods (65C05) Inference from stochastic processes and prediction (62M20)
Cites Work
- Testing the assumptions behind importance sampling
- Time series analysis by state space methods
- Likelihood analysis of non-Gaussian measurement time series
- Central limit theorem for sequential Monte Carlo methods and its application to Bayesian inference
- Lookahead strategies for sequential Monte Carlo
- Filtering via Simulation: Auxiliary Particle Filters
- Particle Markov Chain Monte Carlo Methods
- Title not available (Why is that?)
- Sequential Monte Carlo Methods for Dynamic Systems
- Multivariate Stochastic Variance Models
- Bayesian Inference in Econometric Models Using Monte Carlo Integration
- Weighted Average Importance Sampling and Defensive Mixture Distributions
- BAYESIAN INFERENCE BASED ONLY ON SIMULATED LIKELIHOOD: PARTICLE FILTER ANALYSIS OF DYNAMIC ECONOMIC MODELS
- A sequential smoothing algorithm with linear computational cost
- Efficient Likelihood Evaluation of State-Space Representations
- On some properties of Markov chain Monte Carlo simulation methods based on the particle filter
- Monte Carlo Smoothing for Nonlinear Time Series
- Monte Carlo maximum likelihood estimation for non-Gaussian state space models
- Time Series Analysis of Non-Gaussian Observations Based on State Space Models from Both Classical and Bayesian Perspectives
- A class of adaptive importance sampling weighted EM algorithms for efficient and robust posterior and predictive simulation
- Efficient high-dimensional importance sampling
- Efficient estimation of probit models with correlated errors
- Efficient importance sampling in mixture frameworks
- Efficient importance sampling for ML estimation of SCD models
Cited In (10)
- Approximating optimal SMC proposal distributions in individual-based epidemic models
- Resampling strategy in sequential Monte Carlo for constrained sampling problems
- Controlled sequential Monte Carlo
- Improving MCMC, using efficient importance sampling
- Leverage, Asymmetry, and Heavy Tails in the High-Dimensional Factor Stochastic Volatility Model
- Real-Time Macroeconomic Forecasting With a Heteroscedastic Inversion Copula
- The Gibbs sampler with particle efficient importance sampling for state-space models*
- Modified Cholesky Riemann manifold Hamiltonian Monte Carlo: exploiting sparsity for fast sampling of high-dimensional targets
- Bivariate models for time series of counts: A comparison study between PBINAR models and dynamic factor models
- MCMC for Markov-switching models—Gibbs sampling vs. marginalized likelihood
This page was built for publication: Particle efficient importance sampling
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q894644)
