On the Consistency of Maximum Likelihood Estimators for Causal Network Identification

TL;DR

This paper investigates the consistency of maximum likelihood estimators for identifying the structure and parameters of Bernoulli Autoregressive (BAR) processes, a class of Markov chains modeling causal networks, and provides theoretical guarantees and closed-form solutions.

Contribution

It proves the strong consistency of ML estimators for two BAR model variants and derives closed-form estimators with theoretical validation.

Findings

ML estimators are strongly consistent for the considered BAR models

Closed-form estimators are derived and proven consistent

Theoretical guarantees support causal network identification

Abstract

We consider the problem of identifying parameters of a particular class of Markov chains, called Bernoulli Autoregressive (BAR) processes. The structure of any BAR model is encoded by a directed graph. Incoming edges to a node in the graph indicate that the state of the node at a particular time instant is influenced by the states of the corresponding parental nodes in the previous time instant. The associated edge weights determine the corresponding level of influence from each parental node. In the simplest setup, the Bernoulli parameter of a particular node's state variable is a convex combination of the parental node states in the previous time instant and an additional Bernoulli noise random variable. This paper focuses on the problem of edge weight identification using Maximum Likelihood (ML) estimation and proves that the ML estimator is strongly consistent for two variants of the BAR model. We additionally derive closed-form estimators for the aforementioned two variants and prove their strong consistency.