Consistency under sampling of exponential random graph models

Abstract

The growing availability of network data and of scientific interest in distributed systems has led to the rapid development of statistical models of network structure. Typically, however, these are models for the entire network, while the data consists only of a sampled sub-network. Parameters for the whole network, which is what is of interest, are estimated by applying the model to the sub-network. This assumes that the model is consistent under sampling, or, in terms of the theory of stochastic processes, that it defines a projective family. Focusing on the popular class of exponential random graph models (ERGMs), we show that this apparently trivial condition is in fact violated by many popular and scientifically appealing models, and that satisfying it drastically limits ERGM's expressive power. These results are actually special cases of more general results about exponential families of dependent random variables, which we also prove. Using such results, we offer easily checked conditions for the consistency of maximum likelihood estimation in ERGMs, and discuss some possible constructive responses.

Published in at http://dx.doi.org/10.1214/12-AOS1044 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

References in corpus (7)

• Stochastic blockmodels and community structure in networks
• The large deviation approach to statistical mechanics
• Modeling social networks from sampled data
• Graph limits and exchangeable random graphs
• Estimating and understanding exponential random graph models
• Clustering Stability: An Overview
• Solution for the properties of a clustered network

Cited by in corpus (24)

• Networks beyond pairwise interactions: structure and dynamics
• Exponential-Family Models of Random Graphs: Inference in Finite-, Super-, and Infinite Population Scenarios
• Asymptotics in directed exponential random graph models with an increasing bi-degree sequence
• On the Question of Effective Sample Size in Network Modeling: An Asymptotic Inquiry
• Exponential Random Simplicial Complexes
• Exponential Random Graph models for Little Networks
• Small worlds and clustering in spatial networks
• Asymptotic normality in the maximum entropy models on graphs with an increasing number of parameters
• Concentration and consistency results for canonical and curved exponential-family models of random graphs
• Exponential random graph models for networks with community structure
• Sparse Maximum-Entropy Random Graphs with a Given Power-Law Degree Distribution
• Quantifying Relevance in Learning and Inference
• Social Network Mediation Analysis: a Latent Space Approach
• Consistent structure estimation of exponential-family random graph models with block structure
• Consistency of Maximum Likelihood for Continuous-Space Network Models I
• Bootstrapping Exchangeable Random Graphs
• Testing biological network motif significance with exponential random graph models
• Asymptotic quantization of exponential random graphs
• Time-varying network models
• Sparse power-law network model for reliable statistical predictions based on sampled data
• Projectivity revisited
• Projective, Sparse, and Learnable Latent Position Network Models
• Longitudinal Network Models and Permutation-Uniform Markov Chains
• Graphical Construction of Spatial Gibbs Random Graphs