Open Access
Translator Disclaimer
August 2011 Chain graph models of multivariate regression type for categorical data
Giovanni M. Marchetti, Monia Lupparelli
Bernoulli 17(3): 827-844 (August 2011). DOI: 10.3150/10-BEJ300

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.

Citation

Download Citation

Giovanni M. Marchetti. Monia Lupparelli. "Chain graph models of multivariate regression type for categorical data." Bernoulli 17 (3) 827 - 844, August 2011. https://doi.org/10.3150/10-BEJ300

Information

Published: August 2011
First available in Project Euclid: 7 July 2011

zbMATH: 1221.62108
MathSciNet: MR2817607
Digital Object Identifier: 10.3150/10-BEJ300

Keywords: block-recursive Markov property , discrete chain graph models of type IV , Graphical Markov models , marginal log-linear models , multivariate logistic regression models

Rights: Copyright © 2011 Bernoulli Society for Mathematical Statistics and Probability

JOURNAL ARTICLE
18 PAGES


SHARE
Vol.17 • No. 3 • August 2011
Back to Top