Estimation via Markov chain Monte Carlo

Author

Spall, James C.

Author_Institution

Appl. Phys. Lab., Johns Hopkins Univ., Laurel, MD, USA

Volume

4

fYear

2002

fDate

2002

Firstpage

2559

Abstract

Markov chain Monte Carlo (MCMC) is a powerful means for generating random samples that can be used in computing statistical estimates, numerical integrals, and marginal and joint probabilities. The approach is especially useful in applications where one is forming an estimate based on a multivariate probability distribution or density function that would be hopeless to obtain analytically. In particular, MCMC provides a means for generating samples from joint distributions based on easier sampling from conditional distributions. Over the last 10 to 15 years, the approach has had a large impact on the theory and practice of statistical modeling. On the other hand, MCMC has had relatively little impact (yet) on estimation problems in control. The paper is a survey of popular implementations of MCMC, focusing especially on the two most popular specific implementations of MCMC: Metropolis-Hastings and Gibbs sampling.

Keywords

Markov processes; Monte Carlo methods; sampling methods; state estimation; Gibbs sampling; Markov chain Monte Carlo; Metropolis-Hastings sampling; conditional distributions; density function; joint distributions; multivariate probability distribution; nonnormal state estimation; random samples generation; Bayesian methods; Books; Density functional theory; Monte Carlo methods; Physics computing; Power generation; Probability distribution; Sampling methods; State estimation; System identification;

fLanguage

English

Publisher

ieee

Conference_Titel

American Control Conference, 2002. Proceedings of the 2002

ISSN

0743-1619

Print_ISBN

0-7803-7298-0

Type

conf

DOI

10.1109/ACC.2002.1025170

Filename

1025170