Model-based clustering for social networks Export

@article{handcock:raftery:tantrum:2007, abstract = {Summary. Network models are widely used to represent relations between interacting units or actors. Network data often exhibit transitivity, meaning that two actors that have ties to a third actor are more likely to be tied than actors that do not, homophily by attributes of the actors or dyads, and clustering. Interest often focuses on finding clusters of actors or ties, and the number of groups in the data is typically unknown. We propose a new model, the latent position cluster model, under which the probability of a tie between two actors depends on the distance between them in an unobserved Euclidean 'social space', and the actors' locations in the latent social space arise from a mixture of distributions, each corresponding to a cluster. We propose two estimation methods: a two-stage maximum likelihood method and a fully Bayesian method that uses Markov chain Monte Carlo sampling. The former is quicker and simpler, but the latter performs better. We also propose a Bayesian way of determining the number of clusters that are present by using approximate conditional Bayes factors. Our model represents transitivity, homophily by attributes and clustering simultaneously and does not require the number of clusters to be known. The model makes it easy to simulate realistic networks with clustering, which are potentially useful as inputs to models of more complex systems of which the network is part, such as epidemic models of infectious disease. We apply the model to two networks of social relations. A free software package in the R statistical language, latentnet, is available to analyse data by using the model.}, address = {University of Washington, Seattle, USA; Microsoft adCenter Labs, Redmond, USA}, author = {Handcock, Mark S. and Raftery, Adrian E. and Tantrum, Jeremy M.}, citeulike-article-id = {1226283}, citeulike-linkout-0 = {http://www.blackwell-synergy.com/doi/abs/10.1111/j.1467-985X.2007.00471.x}, citeulike-linkout-1 = {http://dx.doi.org/10.1111/j.1467-985X.2007.00471.x}, citeulike-linkout-2 = {http://www.ingentaconnect.com/content/bpl/rssa/2007/00000170/00000002/art00003}, citeulike-linkout-3 = {http://www3.interscience.wiley.com/cgi-bin/abstract/118522278/ABSTRACT}, doi = {10.1111/j.1467-985X.2007.00471.x}, issn = {0964-1998}, journal = {Journal of the Royal Statistical Society: Series A (Statistics in Society)}, keywords = {bayesian, cluster\_analysis, social\_networks, social\_science\_statistics}, month = {March}, number = {2}, pages = {301--354}, posted-at = {2007-06-21 16:52:46}, priority = {2}, publisher = {Blackwell Publishing}, title = {Model-based clustering for social networks}, url = {http://dx.doi.org/10.1111/j.1467-985X.2007.00471.x}, volume = {170}, year = {2007} }

TY - JOUR ID - handcock:raftery:tantrum:2007 L3 - citeulike-article-id:1226283 N2 - Summary. Network models are widely used to represent relations between interacting units or actors. Network data often exhibit transitivity, meaning that two actors that have ties to a third actor are more likely to be tied than actors that do not, homophily by attributes of the actors or dyads, and clustering. Interest often focuses on finding clusters of actors or ties, and the number of groups in the data is typically unknown. We propose a new model, the latent position cluster model, under which the probability of a tie between two actors depends on the distance between them in an unobserved Euclidean 'social space', and the actors' locations in the latent social space arise from a mixture of distributions, each corresponding to a cluster. We propose two estimation methods: a two-stage maximum likelihood method and a fully Bayesian method that uses Markov chain Monte Carlo sampling. The former is quicker and simpler, but the latter performs better. We also propose a Bayesian way of determining the number of clusters that are present by using approximate conditional Bayes factors. Our model represents transitivity, homophily by attributes and clustering simultaneously and does not require the number of clusters to be known. The model makes it easy to simulate realistic networks with clustering, which are potentially useful as inputs to models of more complex systems of which the network is part, such as epidemic models of infectious disease. We apply the model to two networks of social relations. A free software package in the R statistical language, latentnet, is available to analyse data by using the model. IS - 2 JF - Journal of the Royal Statistical Society: Series A (Statistics in Society) SN - 0964-1998 AD - University of Washington, Seattle, USA; Microsoft adCenter Labs, Redmond, USA EP - 354 TI - Model-based clustering for social networks PB - Blackwell Publishing VL - 170 SP - 301 KW - bayesian KW - cluster_analysis KW - social_networks KW - social_science_statistics AU - Handcock, Mark AU - Raftery, Adrian AU - Tantrum, Jeremy PY - 2007/03// UR - http://dx.doi.org/10.1111/j.1467-985X.2007.00471.x ER -