The Maximum Likelihood Threshold of a Path Diagram

TL;DR

This paper determines the minimum sample size needed for likelihood functions in Gaussian structural equation models to be bounded, considering feedback loops and using graph decomposition techniques.

Contribution

It introduces a method to compute the maximum likelihood threshold for path diagrams with feedback loops, expanding applicability to high-dimensional models.

Findings

Likelihood function is almost surely bounded above the threshold

Likelihood function is almost surely unbounded below the threshold

Standard inference applies to sparse high-dimensional models with feedback loops

Abstract

Linear structural equation models postulate noisy linear relationships between variables of interest. Each model corresponds to a path diagram, which is a mixed graph with directed edges that encode the domains of the linear functions and bidirected edges that indicate possible correlations among noise terms. Using this graphical representation, we determine the maximum likelihood threshold, that is, the minimum sample size at which the likelihood function of a Gaussian structural equation model is almost surely bounded. Our result allows the model to have feedback loops and is based on decomposing the path diagram with respect to the connected components of its bidirected part. We also prove that if the sample size is below the threshold, then the likelihood function is almost surely unbounded. Our work clarifies, in particular, that standard likelihood inference is applicable to sparse high-dimensional models even if they feature feedback loops.