Posterior mean and variance approximation for regression and time series problems

DOI10.1080/02331880701864978zbMATH Open1274.62624OpenAlexW2167843024MaRDI QIDQ3396471FDOQ3396471

Authors

Publication date 18 September 2009

Published in Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/0802.0213

zbMATH Keywords

Kalman filterBayesian inferenceregressiontime seriesstate space modelsconditional independencedynamic linear modelsBayes linear methodsBayesian forecasting

Mathematics Subject Classification ID

Bayesian inference (62F15) Linear regression; mixed models (62J05) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10)

Abstract: This paper develops a methodology for approximating the posterior first two moments of the posterior distribution in Bayesian inference. Partially specified probability models, which are defined only by specifying means and variances, are constructed based upon second-order conditional independence, in order to facilitate posterior updating and prediction of required distributional quantities. Such models are formulated particularly for multivariate regression and time series analysis with unknown observational variance-covariance components. The similarities and differences of these models with the Bayes linear approach are established. Several subclasses of important models, including regression and time series models with errors following multivariate $t$, inverted multivariate $t$ and Wishart distributions, are discussed in detail. Two numerical examples consisting of simulated data and of US investment and change in inventory data illustrate the proposed methodology.

Recommendations

• Accurate Approximations for Posterior Moments and Marginal Densities
• scientific article; zbMATH DE number 3898045
• scientific article; zbMATH DE number 1098811
• scientific article; zbMATH DE number 4024576
• Publication:3200428

Cites work

• scientific article; zbMATH DE number 1808197 (Why is no real title available?)
• scientific article; zbMATH DE number 3426675 (Why is no real title available?)
• scientific article; zbMATH DE number 4211299 (Why is no real title available?)
• scientific article; zbMATH DE number 3942860 (Why is no real title available?)
• scientific article; zbMATH DE number 4100406 (Why is no real title available?)
• scientific article; zbMATH DE number 47310 (Why is no real title available?)
• scientific article; zbMATH DE number 47344 (Why is no real title available?)
• scientific article; zbMATH DE number 1081478 (Why is no real title available?)
• scientific article; zbMATH DE number 1134987 (Why is no real title available?)
• An Analysis of General Exponential Smoothing
• Analysis and Generalisation of a Multivariate Exponential Smoothing Model
• Automatic monitoring and intervention in multivariate dynamic linear models
• Bayes linear kinematics and Bayes linear Bayes graphical models
• Bayes's theorem and the use of prior knowledge in regression analysis
• Bayesian analysis of regression problems
• Bayesian forecasting and dynamic models.
• Bayesian inference in a matrix normal dynamic linear model with unknown covariance matrices
• Decomposition of time series models in state-space form
• Elements of multivariate time series analysis.
• Matricvariate Generalizations of the Multivariate $t$ Distribution and the Inverted Multivariate $t$ Distribution
• Minimax linear regression estimation with symmetric parameter restrictions
• Multivariate discount weighted regression and local level models
• Multivariate statistical modelling based on generalized linear models.
• Observable trend-projecting state-space models
• On Kalman filtering, posterior mode estimation and Fisher scoring in dynamic exponential family regression
• REGRESSION MODELS FOR NON‐STATIONARY CATEGORICAL TIME SERIES
• Smoothness priors analysis of time series
• Time series analysis by state space methods

Cited in

(5)

• scientific article; zbMATH DE number 3945187 (Why is no real title available?)
• Inference of dynamic generalized linear models: on-line computation and appraisal
• Real-time covariance estimation for the local level model
• Dynamic non-parametric monitoring of air-pollution
• Approximating posterior probabilities in a linear model with possibly noninvertible moving average errors

Describes a project that uses

Uses Software

• Fahrmeir

This page was built for publication: Posterior mean and variance approximation for regression and time series problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3396471)