Exponential-Family Models of Random Graphs: Inference in Finite, Super and Infinite Population Scenarios

@article{Schweinberger2017ExponentialFamilyMO,
  title={Exponential-Family Models of Random Graphs: Inference in Finite, Super and Infinite Population Scenarios},
  author={M. Schweinberger and Pavel N. Krivitsky and C. Butts and J. Stewart},
  journal={arXiv: Methodology},
  year={2017}
}
Exponential-family Random Graph Models (ERGMs) constitute a large statistical framework for modeling sparse and dense random graphs, short- and long-tailed degree distributions, covariates, and a wide range of complex dependencies. Special cases of ERGMs are generalized linear models (GLMs), Bernoulli random graphs, $\beta$-models, $p_1$-models, and models related to Markov random fields in spatial statistics and other areas of statistics. While widely used in practice, questions have been… Expand

Figures and Tables from this paper

Consistent structure estimation of exponential-family random graph models with block structure
We consider the challenging problem of statistical inference for exponential-family random graph models based on a single observation of a random graph with complex dependence. To facilitateExpand
Finite Mixtures of ERGMs for Modeling Ensembles of Networks
TLDR
This work develops a Metropolis-within-Gibbs algorithm to conduct fully Bayesian inference and adapt a version of deviance information criterion for missing data models to choose the number of latent heterogeneous generative mechanisms. Expand
Exponential random graph model parameter estimation for very large directed networks
TLDR
An implementation of the recently published Equilibrium Expectation (EE) algorithm for ERGM parameter estimation of large directed networks, and its application to an online social network with over 1.6 million nodes is demonstrated. Expand
Selection of Exponential-Family Random Graph Models via Held-Out Predictive Evaluation (HOPE)
TLDR
This work proposes a predictive evaluation strategy for exponential family random graph models that is analogous to cross-validation and builds on the held-out predictive evaluation scheme, which can assist researchers in improving models by indicating where a model performs poorly, and by quantitatively comparing predictive performance across competing models. Expand
Exponential-Family Random Graph Models for Multi-Layer Networks.
TLDR
Extensions to ERGMs are introduced to address limitations: Conway-Maxwell-Binomial distribution to model the marginal dependence among multiple layers; a "layer logic" language to translate familiar ERGM effects to substantively meaningful interactions of observed layers; and nondegenerate triadic and degree effects. Expand
Impact of survey design on estimation of exponential-family random graph models from egocentrically-sampled data
TLDR
This paper discusses how design choices for egocentric network studies impact statistical estimation and inference for ERGMs, and discusses the importance of harmonising measurement specifications across egos and alters. Expand
Analysis of Networks via the Sparse β-Model
TLDR
This work proposes the Sparse β-Model, a new network model that interpolates the celebrated Erd˝os-R´enyi model and the β-model that assigns one different parameter to each node, and shows via a monotonicity lemma that the seemingly combinatorial computational problem due to the `0-penalty can be overcome by assigning nonzero parameters to those nodes with the largest degrees. Expand
Score-Driven Exponential Random Graphs: A New Class of Time-Varying Parameter Models for Dynamical Networks
TLDR
This work demonstrates the flexibility of the score-driven ERGMs, both as data generating processes and as filters, and proves the advantages of the dynamic version with respect to the static one, and allows for a test discriminating between static or time-varying parameters. Expand
Additive and Multiplicative Effects Network Models
Network datasets typically exhibit certain types of statistical dependencies, such as within-dyad correlation, row and column heterogeneity, and third-order dependence patterns such as transitivityExpand
On Estimation and Inference in Latent Structure Random Graphs
We define a latent structure model (LSM) random graph as a random dot product graph (RDPG) in which the latent position distribution incorporates both probabilistic and geometric constraints,Expand
...
1
2
3
...

References

SHOWING 1-10 OF 274 REFERENCES
Exponential-family Random Network Models
TLDR
This work develops a theory of inference for ERNM when only part of the net- work is observed, as well as specific methodology for missing data, including non- ignorable mechanisms for network-based sampling designs and for latent class models. Expand
Concentration and consistency results for canonical and curved exponential-family models of random graphs
Statistical inference for exponential-family models of random graphs with dependent edges is challenging. We stress the importance of additional structure and show that additional structureExpand
New Specifications for Exponential Random Graph Models
The most promising class of statistical models for expressing structural properties of social networks observed at one moment in time is the class of exponential random graph models (ERGMs), alsoExpand
DERGMs: Degeneracy-restricted exponential random graph models
TLDR
A new exponential family of models for random graphs that build on the standard ERGM framework is proposed, and a new parameter based on the graph-theoretic notion of degeneracy, a measure of sparsity whose value is low in real-worlds networks is introduced. Expand
CONSISTENCY UNDER SAMPLING OF EXPONENTIAL RANDOM GRAPH MODELS.
TLDR
It is shown 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. Expand
On the geometry of discrete exponential families with application to exponential random graph models
There has been an explosion of interest in statistical models for analyzing network data, and considerable interest in the class of exponential random graph (ERG) models, especially in connectionExpand
Marginalized Exponential Random Graph Models
Exponential random graph models (ERGMs) are a popular tool for modeling social networks representing relational data, such as working relationships or friendships. Data on exogenous variablesExpand
Consistent structure estimation of exponential-family random graph models with block structure
We consider the challenging problem of statistical inference for exponential-family random graph models based on a single observation of a random graph with complex dependence. To facilitateExpand
Bayesian model selection for exponential random graph models
TLDR
The contribution of this paper is the development of a fully Bayesian model selection method based on a reversible jump Markov chain Monte Carlo algorithm extension of Caimo and Friel (2011) which estimates the posterior probability for each competing model. Expand
Inference in Curved Exponential Family Models for Networks
Network data arise in a wide variety of applications. Although descriptive statistics for networks abound in the literature, the science of fitting statistical models to complex network data is stillExpand
...
1
2
3
4
5
...