Binary Models for Marginal Independence

Details Binary Models for Marginal Independence Binary Models for Marginal Independence

2007-07-25

arxiv.org/abs/0707.3794v1

Journal of the Royal Statistical Society Series B 2008, Vol. 70, No. 2, 287-309

Mathematics

Statistics Theory

Scientific paper

10.1111/j.1467-9868.2007.00636.x

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. Focusing on binary variables, we present a model class that provides a framework for modelling marginal independences in contingency tables. The approach taken is graphical and draws on analogies to multivariate Gaussian models for marginal independence. For the graphical model representation we use bi-directed graphs, which are in the tradition of path diagrams. We show how the models can be parameterized in a simple fashion, and how maximum likelihood estimation can be performed using a version of the Iterated Conditional Fitting algorithm. Finally we consider combining these models with symmetry restrictions.

Affiliated with

Also associated with

No associations

Rating

Binary Models for Marginal Independence does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Binary Models for Marginal Independence, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Binary Models for Marginal Independence will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-547454