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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Karwa, Vishesh, Pati, Debdeep, Petrović, Sonja, Solus, Liam, Alexeev, Nikita, Raič, Mateja, Wilburne, Dane, Williams, Robert, Yan, Bowei
Format: Preprint
Published: 2016
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911789626687488
author Karwa, Vishesh
Pati, Debdeep
Petrović, Sonja
Solus, Liam
Alexeev, Nikita
Raič, Mateja
Wilburne, Dane
Williams, Robert
Yan, Bowei
author_facet Karwa, Vishesh
Pati, Debdeep
Petrović, Sonja
Solus, Liam
Alexeev, Nikita
Raič, Mateja
Wilburne, Dane
Williams, Robert
Yan, Bowei
contents 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 \emph{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 behavior. 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.
format Preprint
id arxiv_https___arxiv_org_abs_1612_06040
institution arXiv
publishDate 2016
record_format arxiv
spellingShingle Monte Carlo goodness-of-fit tests for degree corrected and related stochastic blockmodels
Karwa, Vishesh
Pati, Debdeep
Petrović, Sonja
Solus, Liam
Alexeev, Nikita
Raič, Mateja
Wilburne, Dane
Williams, Robert
Yan, Bowei
Methodology
Statistics Theory
62R01, 05C82
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 \emph{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 behavior. 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.
title Monte Carlo goodness-of-fit tests for degree corrected and related stochastic blockmodels
topic Methodology
Statistics Theory
62R01, 05C82
url https://arxiv.org/abs/1612.06040