In this paper we discuss a class of models of marginal independence for a set of categorical variables called discrete covariance graph models. These models, introduced by Drton & Richardson (2005) in the binary case, are a useful addition to standard graphical log-linear models which are represented by an undirected graph and encode conditional independencies, Lauritzen (1996).
Parameterization and fitting of discrete covariance graph models
LUPPARELLI, MONIA;
2006
Abstract
In this paper we discuss a class of models of marginal independence for a set of categorical variables called discrete covariance graph models. These models, introduced by Drton & Richardson (2005) in the binary case, are a useful addition to standard graphical log-linear models which are represented by an undirected graph and encode conditional independencies, Lauritzen (1996).File in questo prodotto:
Eventuali allegati, non sono esposti
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
