Quantification of prior information revised
From MaRDI portal
The paper deals with Bayesian estimation. The algorithm which is proposed consists of the following steps. (i) The individual information pieces are converted into a common form called fictitious data; (ii) posterior degrees of belief (conditioned by available real data) are assigned to individual information pieces; (iii) the constructed posterior pdf on estimated parameters is taken as a weighted geometric mean of posterior pdfs obtained for individual prior information items (the degrees of belief found in (ii) are used as weights).
Recommendations
- Assessment of Prior Distributions based on Information Theory
- The extraction of information from multiple point estimates
- Bayesian information fusion based on the D-S evidence theory
- Application of evidence theory in information fusion of multiple sources in Bayesian analysis
- scientific article; zbMATH DE number 1395885
Cites work
- Factorization methods for discrete sequential estimation
- scientific article; zbMATH DE number 3602484 (Why is no real title available?)
- scientific article; zbMATH DE number 3997615 (Why is no real title available?)
- Identification of reality in Bayesian context
- Interactive system identification: prospects and pitfalls
- On Information and Sufficiency
Cited in
(13)- Accounting of prior information in paramacrosystems
- Comparison of uncertainty evaluation method based on Bayesian principle
- Application of evidence theory in information fusion of multiple sources in Bayesian analysis
- The extraction of information from multiple point estimates
- Assessment of Prior Distributions based on Information Theory
- scientific article; zbMATH DE number 1551908 (Why is no real title available?)
- A comparison of two methods for obtaining a collective posterior distribution
- Estimation and prediction with ARMMAX model: a mixture of ARMAX models with common ARX part
- Bayesian information fusion based on the D-S evidence theory
- scientific article; zbMATH DE number 1395885 (Why is no real title available?)
- Incorporating prior information when true priors are unknown: an information-theoretic approach for increasing efficiency in estimation
- On Supra-Bayesian weighted combination on available data determined by Kerridge inaccuracy and entropy.
- Bayesian M-T clustering for reduced parameterisation of Markov chains used for nonlinear adaptive elements
This page was built for publication: Quantification of prior information revised
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2708069)