Markov Chain Monte Carlo Estimation of Exponential Random Graph Models

By Tom A. B. Snijders. Journal of Social Structure, 2002

826 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/c7c09c5d3b84edfdc77776a43bcee1d1c735ef59

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Mixing patterns in networks. (2002, methodology): “Instead, therefore, we use a Monte Carlo sampling scheme which is essentially equivalent to the Metropolis–Hastings method widely used in the mathematical and social sciences for generating model networks [55, 56].”
MODELING SOCIAL NETWORKS FROM SAMPLED DATA. (2010, methodology): “The development of these methods for social network data has been considered by Corander, Dahmstr¨om and Dahmstr¨om (1998); Crouch, Wasserman and Trachtenberg (1998); Snijders (2002); Handcock (2002); Corander, Dahmstr¨om and Dahmstr¨om (2002); Hunter and Handcock (2006).”
A state-space mixed membership blockmodel for dynamic network tomography (2008, methodology): “Among these models, some variants of the ERGMs, such as the stochastic block models [Holland, Laskey and Leinhardt (1983); Fienberg, Meyer and Wasserman (1985); Wasserman and Pattison (1996); Snijders (2002)], cluster network vertices based on their structural equivalency [Lorrain and White (1971)].”
Birds of a feather, or friend of a friend? using exponential random graph models to investigate adolescent social networks* (2009, methodology): “The likelihood can be approximated using Markov chain Monte Carlo simulation methods (MCMC; Geyer and Thompson 1992; Snijders 2002), which generate a sample from the space of possible networks to estimate the θ vector.”
Inference in Curved Exponential Family Models for Networks (2006, methodology): “In reality, these “statistics” are not quite statistics because they are based on parameters; however, Snijders et al. (2006) assumed that these parameters are fixed and known. In this article, we relax this restriction and estimate these additional parameters. The alternating k-star and alternating”
Statistical mechanics of networks. (2004, methodology): “Today, exponential random graphs are in common use within the statistics and social network analysis communities as a practical tool for modeling networks and several standard computer tools are available for simulating and manipulating them, including Prepstar, ERGM, and Siena [22].”
Bayesian Parameter Estimation for Latent Markov Random Fields and Social Networks (2012, methodology): “These methods have not been used before in the ERGM literature and address some of the known problems with MCMC described in Snijders (2002).”
Mixed Membership Stochastic Blockmodels (2007, background): “In statistics, this line of research has been extended in various contexts over the years (Fienberg et al., 1985; Wasserman and Pattison, 1996; Snijders, 2002; Hoff et al., 2002; Doreian et al., 2004).”
Detecting communities and their evolutions in dynamic social networks—a Bayesian approach (2011, methodology): “This model was originally proposed by Holland and Leinhardt (1976) and was further extended by others, e.g. (Fienberg et al. 1985; Ho et al. 2002; Shortreed et al. 2006; Snijders 2002; Wasserman and Pattison 1996).”
The analysis of social networks (2008, methodology): “An alternative approach (Snijders 2002) available in StOCNET (Huisman and Van Duijn 2004, 2005) relies on a stochastic approximation algorithm.”
9. Neighborhood-Based Models for Social Networks (2002, methodology): “7 The development of feasible methods for maximum likelihood estimation is an area of active research (for example, Corander et al., 1998; Crouch & Wasserman, 1998; Snijders, 2001).”
Econometrics of Network Formation (2016, methodology): “Therefore, the literature has moved to employing Markov Chain Monte Carlo (MCMC) sampling techniques (Snijders, 2002; Handcock, 2003).”
Specification of Exponential-Family Random Graph Models: Terms and Computational Aspects. (2008, background): “See Snijders (2002) or Snijders and van Duijn (2002) for details on the Robbins-Monro algorithm for ERGM estimation.”