Marginal Log-linear Parameters and their Collapsibility for Categorical Data

TL;DR

This paper explores the properties, collapsibility conditions, and independence relations of marginal log-linear parameters in multidimensional contingency tables, providing verifiable criteria and real-data illustrations.

Contribution

It introduces general collapsibility concepts for marginal log-linear models, deriving necessary and sufficient conditions, and connects these to variable independence and model smoothness.

Findings

Derived verifiable conditions for collapsibility and strict collapsibility.

Connected strict collapsibility to various independence structures.

Illustrated results with real-life datasets.

Abstract

We consider marginal log-linear models for parameterizing distributions on multidimensional contingency tables. These models generalize ordinary log-linear and multivariate logistic models, besides several others. First, we obtain some characteristic properties of marginal log-linear parameters. Then we define collapsibility and strict collapsibility of these parameters in a general sense. Several necessary and sufficient conditions for collapsibility and strict collapsibility are derived based on simple functions of only the cell probabilities, which are easily verifiable. These include results for an arbitrary set of marginal log-linear parameters having some common effects. The connections of strict collapsibility to various forms of independence of the variables are explored. We analyze some real-life datasets to illustrate the above results on collapsibility and strict collapsibility. Finally, we obtain a result relating parameters with the same effect but different margins for an arbitrary table, and demonstrate smoothness of marginal log-linear models under collapsibility conditions.