Sequential Bayesian inference for static parameters in dynamic state space models
From MaRDI portal
Publication:1663121
DOI10.1016/J.CSDA.2018.05.018zbMATH Open1469.62023arXiv1408.4559OpenAlexW2964239615WikidataQ129732278 ScholiaQ129732278MaRDI QIDQ1663121FDOQ1663121
Simon P. Wilson, Arnab Bhattacharya
Publication date: 21 August 2018
Published in: Computational Statistics and Data Analysis (Search for Journal in Brave)
Abstract: A method for sequential Bayesian inference of the static parameters of a dynamic state space model is proposed. The method is based on the observation that many dynamic state space models have a relatively small number of static parameters (or hyper-parameters), so that in principle the posterior can be computed and stored on a discrete grid of practical size which can be tracked dynamically. Further to this, this approach is able to use any existing methodology which computes the filtering and prediction distributions of the state process. Kalman filter and its extensions to non-linear/non-Gaussian situations have been used in this paper. This is illustrated using several applications: linear Gaussian model, Binomial model, stochastic volatility model and the extremely non-linear univariate non-stationary growth model. Performance has been compared to both existing on-line method and off-line methods.
Full work available at URL: https://arxiv.org/abs/1408.4559
Computational methods for problems pertaining to statistics (62-08) Bayesian inference (62F15) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Inference from stochastic processes and prediction (62M20) Sequential estimation (62L12)
Cites Work
- Gaussian Markov Random Fields
- Sequential Monte Carlo Methods in Practice
- Title not available (Why is that?)
- Title not available (Why is that?)
- Multivariate adaptive regression splines
- Time series analysis by state space methods
- Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations (with discussion)
- Spatial variation. 2nd ed
- Inference in hidden Markov models.
- Marginal Likelihood from the Gibbs Output
- Title not available (Why is that?)
- Filtering via Simulation: Auxiliary Particle Filters
- Particle Markov Chain Monte Carlo Methods
- On Estimation of a Probability Density Function and Mode
- SMC2: An Efficient Algorithm for Sequential Analysis of State Space Models
- Multivariate statistical modelling based on generalized linear models.
- Bayesian forecasting and dynamic models.
- A practical guide to splines
- Particle approximations of the score and observed information matrix in state space models with application to parameter estimation
- A Bayesian Formulation of Exploratory Data Analysis and Goodness‐of‐fit Testing*
- Polynomial splines and their tensor products in extended linear modeling. (With discussions)
- The problem of the Nile: Conditional solution to a changepoint problem
- Iterated filtering
- On particle methods for parameter estimation in state-space models
- Title not available (Why is that?)
- Particle learning and smoothing
- Detectability and Stabilizability of Time-Varying Discrete-Time Linear Systems
- High dimensional polynomial interpolation on sparse grids
- Non-Gaussian State-Space Modeling of Nonstationary Time Series
- Title not available (Why is that?)
- Gaussian filters for nonlinear filtering problems
- Stochastic Stability of the Extended Kalman Filter With Intermittent Observations
- Gaussian particle filtering
- Posterior Mode Estimation by Extended Kalman Filtering for Multivariate Dynamic Generalized Linear Models
- Error bounds for polynomial tensor product interpolation
- Lyapunov Exponents for Finite State Nonlinear Filtering
- Minimum error bounds for multidimensional spline approximation
- Extensible Grids: Uniform Sampling on a Space Filling Curve
Cited In (6)
- Temporal state change Bayesian networks for modeling of evolving multivariate state sequences: model, structure discovery and parameter estimation
- Bayesian inference in nonparametric dynamic state-space models
- Sequential parameter learning and filtering in structured autoregressive state-space models
- Following a moving target -- Monte Carlo inference for dynamic Bayesian models
- Updating variational Bayes: fast sequential posterior inference
- Approximate Bayesian inference for discretely observed continuous‐time multi‐state models
Uses Software
This page was built for publication: Sequential Bayesian inference for static parameters in dynamic state space models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1663121)
