Sampled Networks
Sampling design and inference for networks
Many real-world networks, whether social or epidemic, are not practical to observe directly. Instead, a network may be observed indirectly, from the point of view of a sample of individuals in the network. Or, only some of the relations may be observed, and noisily at that. Or, we may observe a sample of networks from a larger population.
My work develops methodology and software to permit network structure to be recovered from such indirectly observed relational data.
Related papers
Pavel N. Krivitsky, Pietro Coletti, and Niel Hens, A tale of two datasets: Representativeness and generalisability of inference for samples of networks,
Journal of the American Statistical Association, pp. 1–21, 2023. doi:10.1080/01621459.2023.2242627
Pavel N. Krivitsky, Pietro Coletti, and Niel Hens, Rejoinder to discussion of “A tale of two datasets: Representativeness and generalisability of inference for samples of networks”,
Journal of the American Statistical Association, vol. 118, no. 544, pp. 2235–2238, 2023. doi:10.1080/01621459.2023.2280383
Pavel N. Krivitsky, Martina Morris, and Michał Bojanowski, Impact of survey design on estimation of exponential-family random graph models from egocentrically-sampled data,
Social Networks, 2021. doi:10.1016/j.socnet.2020.10.001
Michael Schweinberger, Pavel N. Krivitsky, Carter T. Butts, and Jonathan R. Stewart, Exponential-family models of random graphs: Inference in finite, super and infinite population scenarios,
Statistical Science, vol. 35, no. 4, pp. 627–662, 2020. doi:10.1214/19-STS743
Pavel N. Krivitsky and Martina Morris, Inference for social network models from egocentrically-sampled data, with application to understanding persistent racial disparities in HIV prevalence in the US,
Annals of Applied Statistics, vol. 11, no. 1, pp. 427–455, 2017. doi:10.1214/16-AOAS1010
Vishesh Karwa, Pavel N. Krivitsky, and Aleksandra B. Slavković, Sharing social network data: Differentially private estimation of exponential-family random graph models,
Journal of the Royal Statistical Society, Series C, vol. 66, no. 3, pp. 481–500, 2017. doi:10.1111/rssc.12185
Pavel N. Krivitsky and Eric D. Kolaczyk, On the question of effective sample size in network modeling: An asymptotic inquiry,
Statistical Science, vol. 30, no. 2, pp. 184–198, 2015. doi:10.1214/14-STS502
Vishesh Karwa, Aleksandra B Slavković, and Pavel Krivitsky, Differentially private exponential random graphs,
In Proc. Privacy in statistical databases, 2014, vol. 8744, pp. 143–155. doi:10.1007/978-3-319-11257-2_12
Pavel N. Krivitsky, Modeling of dynamic networks based on egocentric data with durational information,
Pennsylvania State University Department of Statistics, no. 2012-01, 2012. arXiv:2203.06866
Pavel N. Krivitsky, Mark S. Handcock, and Martina Morris, Adjusting for network size and composition effects in exponential-family random graph models,
Statistical Methodology, vol. 8, no. 4, pp. 319–339, 2011. doi:10.1016/j.stamet.2011.01.005
Related packages
ergm
: Fit, Simulate and Diagnose Exponential-Family Models for Networks
ergm.multi
: Fit, Simulate and Diagnose Exponential-Family Models for Multiple or Multilayer Networks
ergm.ego
: Fit, Simulate and Diagnose Exponential-Family Random Graph Models to Egocentrically Sampled Network Data
egor
: Import and Analyse Ego-Centered Network Data