Abstract
In social network analysis, logistic regression models have been widely used to establish the relationship between the response variable and covariates. However, such models often require the network relationships to be mutually independent, after controlling for a set of covariates. To assess the validity of this assumption, we propose test statistics, under the logistic regression setting, for three important social network drivers. They are, respectively, reciprocity, centrality, and transitivity. The asymptotic distributions of those test statistics are obtained. Extensive simulation studies are also presented to demonstrate their finite sample performance and usefulness.
Similar content being viewed by others
References
de Miguel Luken V, Tranmer M. Personal support networks of immigrants to Spain: A multilevel analysis. Social Networks, 2010, 32: 253–262
Frank O, Strauss D. Markov graphs. J Amer Statist Assoc, 1986, 81: 832–842
Gozz S, D’Agata R. Social networks and political participation in a Sicilian community context. Procedia Soc Behav Sci, 2010, 4: 49–58
Hanneman R A, Riddle M. Introduction to Social Network Methods. Http://faculty.ucr.edu/~hanneman/nettext, 2005
Hoff P D, Raftery A E, Handcock M S. Latent space approaches to social network analysis. J Amer Statist Assoc, 2002, 97: 1090–1098
Holland P W, Leinhardt S. An exponential family of probability distributions for directed graphs. J Amer Statist Assoc, 1981, 76: 33–50
Hunter D R, Goodreau S M, Handcock M S. Goodness of fit of social network models. J Amer Statist Assoc, 2008, 103: 248–258
Knoke D, Yang S. Social Network Analysis. London: Sage, 2008
Nowicki K, Snijders T A B. Estimation and prediction for stochastic block structures. J Amer Statist Assoc, 2001, 96: 1077–1087
Oloritun R O, Madan A, Pentland A, et al. Identifying close friendships in a sensed social network. Procedia Soc Behav Sci, 2013, 79: 18–26
Shao J. Mathematical Statistics. New York: Springer, 1999
Snijders T A B. Markov chain monte carlo estimation of exponential random graph models. J Soc Structure, 2002, 3: 1–40
Strauss D, Ikeda M. Pseudolikelihood estimation for social networks. J Amer Statist Assoc, 1990, 85, 204–212
Wang Y J, Wong G Y. Stochastic blockmodels for directed graphs. J Amer Statist Assoc, 1987, 82: 8–19
Wasserman S, Faust K. Social Network Analysis: Methods and Applications. New York: Cambridge University Press, 1994
Wasserman S, Pattison P. Logit models and logistic regressions for social networks: An introduction to Markov graphs and p*. Psychometrika, 1996, 61: 401–425
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Pan, R., Wang, H. A note on testing conditional independence for social network analysis. Sci. China Math. 58, 1179–1190 (2015). https://doi.org/10.1007/s11425-015-4998-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11425-015-4998-0
Keywords
- centrality
- conditional independence
- logistic regression model
- reciprocity
- social network analysis
- transitivity