Bayesian MAP model selection of chain event graphs
Freeman, Guy and Smith, J. Q.. (2011) Bayesian MAP model selection of chain event graphs. Journal of Multivariate Analysis, Vol.102 (No.7). pp. 1152-1165. ISSN 0047259XFull text not available from this repository.
Official URL: http://dx.doi.org/10.1016/j.jmva.2011.03.008
Chain event graphs are graphical models that while retaining most of the structural advantages of Bayesian networks for model interrogation, propagation and learning, more naturally encode asymmetric state spaces and the order in which events happen than Bayesian networks do. In addition, the class of models that can be represented by chain event graphs for a finite set of discrete variables is a strict superset of the class that can be described by Bayesian networks. In this paper we demonstrate how with complete sampling, conjugate closed form model selection based on product Dirichlet priors is possible, and prove that suitable homogeneity assumptions characterise the product Dirichlet prior on this class of models. We demonstrate our techniques using two educational examples. (C) 2011 Elsevier Inc. All rights reserved.
|Item Type:||Journal Article|
|Subjects:||H Social Sciences > HA Statistics
Q Science > QA Mathematics
|Divisions:||Faculty of Science > Statistics|
|Library of Congress Subject Headings (LCSH):||Bayesian statistical decision theory, Mathematical models, Mathematical statistics, Dirichlet problem, Distribution (Probability theory)|
|Journal or Publication Title:||Journal of Multivariate Analysis|
|Official Date:||August 2011|
|Page Range:||pp. 1152-1165|
|Funder:||Engineering and Physical Sciences Research Council (EPSRC)|
|Grant number:||EP/F036752/1 (EPSRC)|
Actions (login required)