The Statistics Seminar Speaker for December 2 is Helene Massam, professor in the department of Mathematics and Statistics at York University. For more information, including Massam's publications list, visit her webpage.
Title: A New Prior for Discrete DAG Models with a Restricted Set of Directions
Abstract: In the present literature, prior distributions for discrete directed acyclic graph (DAG) models are either derived from the Dirichlet distribution on the complete model or consists of a set of different Dirichlet priors for each vertex of the DAG and each configuration of its parents.
In this talk, we develop a new family of conjugate prior distributions for the cell probability parameters of discrete graphical models Markov with respect to a set $\cP$ of moral directed acyclic graphs with skeleton a given decomposable graph $G$. This family, which we call the $\cP$-Dirichlet, is a generalization of the hyper Dirichlet: it keeps the directed strong hyper Markov property of the hyper Dirichlet for every DAG in $\cP$ but increases the flexibility in the choice of its parameters, i.e. the hyper parameters.
We also give a characterization of this $\cP$-Dirichlet which yields, as corollaries, a characterization of the hyper Dirichlet and a characterization of the Dirichlet.
Refreshments will be served after the seminar in 1181 Comstock Hall.