Chain graph models of multivariate regression type for categorical data

Abstract

We discuss a class of chain graph models for categorical variables defined by what we call a multivariate regression chain graph Markov property. First, the set of local independencies of these models is shown to be Markov equivalent to those of a chain graph model recently defined in the literature. Next we provide a parametrization based on a sequence of generalized linear models with a multivariate logistic link function that captures all independence constraints in any chain graph model of this kind.

Published in at http://dx.doi.org/10.3150/10-BEJ300 the Bernoulli (http://isi.cbs.nl/bernoulli/) by the International Statistical Institute/Bernoulli Society (http://isi.cbs.nl/BS/bshome.htm)

References in corpus (2)

• Binary Models for Marginal Independence
• Discrete chain graph models

Cited by in corpus (11)

• Marginal log-linear parameters for graphical Markov models
• Probability distributions with summary graph structure
• Log-mean linear models for binary data
• Marginalization and Conditioning for LWF Chain Graphs
• Pairwise Markov properties for regression graphs
• Concepts and a case study for a flexible class of graphical Markov models
• On the Properties of MVR Chain Graphs
• Case-control studies for rare diseases: improved estimation of several risks and of feature dependences
• Structural Learning of Multivariate Regression Chain Graphs via Decomposition
• Graphical Markov models: overview
• Multiple Hidden Markov Models for Categorical Time Series