Latent Space Models

Latent variable models for relational data

A powerful approach to modeling complex network structure is through latent variable models, in which an unobserved (latent) social space in which actors interact and/or unobserved attributes of actors are postulated that account for observed network structure. My interest is in extending them to dynamic network data, applying them to voting data, and efficient Bayesian inference.

Luke Mazur, Thomas Suesse, and Pavel N. Krivitsky, Investigating foreign portfolio investment holdings: Gravity model with social network analysis, International Journal of Finance & Economics, vol. 27, no. 1, pp. 554–570, 2020. doi:10.1002/ijfe.2168

Pavel N. Krivitsky, Mark S. Handcock, Adrian E. Raftery, and Peter D. Hoff, Representing degree distributions, clustering, and homophily in social networks with latent cluster random effects models, Social Networks, vol. 31, no. 3, pp. 204–213, 2009. doi:10.1016/j.socnet.2009.04.001

Pavel N. Krivitsky and Mark S. Handcock, Fitting position latent cluster models for social networks with, Journal of Statistical Software, vol. 24, no. 5, pp. 1–23, 2008. doi:10.18637/jss.v024.i05

latentnet: Latent Position and Cluster Models for Statistical Networks