Seminars

General Departmental Seminar Series

 

Binary Models for Marginal Independence

Professor Mathias Drton from
the Department of Statistics,  University of Chicago

Friday, April 21, 2006
12:00 pm     

5235/75 MSC

ABSTRACT

Log-linear models are a classical tool for the analysis of contingency tables.  In particular, the subclass of graphical log-linear models provides a general framework for modelling conditional independences. However, with the exception of special structures, marginal independence hypotheses cannot be accommodated by these traditional models.  For example, it is not possible to formulate a model for four variables (A,B,X,Y) such that A is independent of B, and X is independent of Y (and no other restrictions are imposed).  Focusing on binary variables, I will present a new model class that provides a framework for modelling marginal independences in contingency tables.  The approach taken is graphical and based on bi-directed graphs, which are in the tradition of path diagrams. In many respects, the resulting models are dual to graphical log-linear models. (joint work with Thomas Richardson, University of Washington)