Probability distributions with summary graph structure

TL;DR

This paper introduces summary graphs for representing and analyzing the independence structures of probability distributions, especially after marginalizing or conditioning, to identify invariances and potential distortions.

Contribution

It proposes a novel class of summary graphs that preserve independence structures under marginalization and conditioning, enhancing understanding of complex probabilistic models.

Findings

Summary graphs reflect independence structures after marginalization and conditioning.

They can identify invariances and distortions in dependencies.

Operators for matrix representations facilitate analysis of these graphs.

Abstract

A set of independence statements may define the independence structure of interest in a family of joint probability distributions. This structure is often captured by a graph that consists of nodes representing the random variables and of edges that couple node pairs. One important class contains regression graphs. Regression graphs are a type of so-called chain graph and describe stepwise processes, in which at each step single or joint responses are generated given the relevant explanatory variables in their past. For joint densities that result after possible marginalising or conditioning, we introduce summary graphs. These graphs reflect the independence structure implied by the generating process for the reduced set of variables and they preserve the implied independences after additional marginalising and conditioning. They can identify generating dependences that remain unchanged and alert to possibly severe distortions due to direct and indirect confounding. Operators for matrix representations of graphs are used to derive these properties of summary graphs and to translate them into special types of paths in graphs.