Monte Carlo goodness-of-fit tests for degree corrected and related stochastic blockmodels

Abstract

We construct Bayesian and frequentist finite-sample goodness-of-fit tests for three different variants of the stochastic blockmodel for network data. Since all of the stochastic blockmodel variants are log-linear in form when block assignments are known, the tests for the latent block model versions combine a block membership estimator with the algebraic statistics machinery for testing goodness-of-fit in log-linear models. We describe Markov bases and marginal polytopes of the variants of the stochastic blockmodel and discuss how both facilitate the development of goodness-of-fit tests and understanding of model behaviour. The general testing methodology developed here extends to any finite mixture of log-linear models on discrete data, and as such is the first application of the algebraic statistics machinery for latent-variable models.

Document Details

Document Type
Pub Defense Publication
Publication Date
Sep 15, 2023
Source ID
10.1093/jrsssb/qkad084

Entities

People

  • Bowei Yan
  • Dane Wilburne
  • Debdeep Pati
  • Liam Solus
  • Mateja Raič
  • Nikita Alexeev
  • Robert Williams
  • Sonja Petrović
  • Vishesh Karwa

Organizations

  • Air Force Office of Scientific Research
  • Illinois Institute of Technology
  • MITRE Corporation
  • National Science Foundation
  • Office of Naval Research
  • Rose–Hulman Institute of Technology
  • Royal Institute of Technology
  • Simons Foundation
  • Temple University
  • Texas A&M University
  • The Citadel
  • United States Department of Energy
  • University of Illinois at Chicago

Tags

Fields of Study

  • Mathematics

Readers

  • Fire Suppression Systems Design.
  • Graph Algorithms and Convex Optimization.
  • Statistical inference.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms