A structural Markov property for decomposable graph laws that allows control of clique intersections

Green, PJ; Thomas, A

A structural Markov property for decomposable graph laws that allows control of clique intersections

Green, PJ

Thomas, A

Permalink

Publication Type:: Journal Article
Citation:: Biometrika, 2018, 105 (1), pp. 19 - 29
Issue Date:: 2018-03-01

Closed Access

	Filename	Description	Size
	asx072.pdf	Published Version	377.73 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Green, PJ https://orcid.org/0000-0002-4367-4756	en_US
dc.contributor.author	Thomas, A	en_US
dc.date.issued	2018-03-01	en_US
dc.identifier.citation	Biometrika, 2018, 105 (1), pp. 19 - 29	en_US
dc.identifier.issn	0006-3444	en_US
dc.identifier.uri	http://hdl.handle.net/10453/128171
dc.description.abstract	© 2017 Biometrika Trust. We present a new kind of structural Markov property for probabilistic laws on decomposable graphs, which allows the explicit control of interactions between cliques and so is capable of encoding some interesting structure. We prove the equivalence of this property to an exponential family assumption, and discuss identifiability, modelling, inferential and computational implications.	en_US
dc.relation.ispartof	Biometrika	en_US
dc.relation.isbasedon	10.1093/biomet/asx072	en_US
dc.subject.classification	Statistics & Probability	en_US
dc.title	A structural Markov property for decomposable graph laws that allows control of clique intersections	en_US
dc.type	Journal Article
utslib.citation.volume	1	en_US
utslib.citation.volume	105	en_US
utslib.for	0104 Statistics	en_US
utslib.for	1403 Econometrics	en_US
utslib.for	0103 Numerical and Computational Mathematics	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Science
pubs.organisational-group	/University of Technology Sydney/Faculty of Science/School of Mathematical and Physical Sciences
utslib.copyright.status	closed_access
pubs.issue	1	en_US
pubs.publication-status	Published	en_US
pubs.volume	105	en_US

Abstract:

© 2017 Biometrika Trust. We present a new kind of structural Markov property for probabilistic laws on decomposable graphs, which allows the explicit control of interactions between cliques and so is capable of encoding some interesting structure. We prove the equivalence of this property to an exponential family assumption, and discuss identifiability, modelling, inferential and computational implications.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/128171