Existence of maximum likelihood estimates in exponential random graph models

2022/04/10 by Henry Bayly, Bayly, Henry, Aditya Khanna +3
Mathematics · #Markov Chains and Monte Carlo Methods

paper · pdf · doi:10.48550/arxiv.2204.04757

Abstract

We present a streamlined proof of the foundational result in the theory of exponential random graph models (ERGMs) that the maximum likelihood estimate exists if and only if the target statistic lies in the relative interior of the convex hull of the set of realizable statistics. .

Related

• Maximum likelihood estimation for discrete exponential families and random graphs
• Improving ERGM Starting Values Using Simulated Annealing
• On the Geometry of Discrete Exponential Families with Application to Exponential Random Graph Models
• Maximum likelihood thresholds via graph rigidity
• Stein's method of moment estimators for local dependency exponential random graph models