# zbMATH — the first resource for mathematics

Using retrospective sampling to estimate models of relationship status in large longitudinal social networks. (English) Zbl 06984104
Summary: Estimation of longitudinal models of relationship status between all pairs of individuals (dyads) in social networks is challenging due to the complex inter-dependencies among observations and lengthy computation times. To reduce the computational burden of model estimation, a method is developed that subsamples the “always-null” dyads in which no relationships develop throughout the period of observation. The informative sampling process is accounted for by weighting the likelihood contributions of the observations by the inverses of the sampling probabilities. This weighted-likelihood estimation method is implemented using Bayesian computation and evaluated in terms of its bias, efficiency, and speed of computation under various settings. Comparisons are also made to a full information likelihood-based procedure that is only feasible to compute when limited follow-up observations are available. Calculations are performed on two real social networks of very different sizes. The easily computed weighted-likelihood procedure closely approximates the corresponding estimates for the full network, even when using low sub-sampling fractions. The fast computation times make the weighted-likelihood approach practical and able to be applied to networks of any size.

##### MSC:
 62 Statistics
Full Text:
##### References:
 [1] Browne, W. J.; Draper, D.; Goldstein, H.; Rasbash, J., Bayesian and likelihood methods for Fitting multilevel models with complex level-1 variation, Comput. Statist. Data Anal., 39, 2, 203-225, (2002) · Zbl 1132.62312 [2] Christakis, N.; Fowler, J., The spread of obesity in a large social network over 32 years, N. Engl. J. Med., 357, 370-379, (2007) [3] Christakis, N.; Fowler, J., Dynamics of smoking behavior in a large social network, N. Engl. J. Med., 358, 2249-2258, (2008) [4] Cooper, N. J.; Lambert, P. C.; Abrams, K. R.; Sutton, A. J., Predicting costs over time using Bayesian Markov chain Monte Carlo methods: an application to early inflammatory polyarthritus, Health Econ., 16, 37-56, (2007) [5] Duijn, M. V.; Snijders, T. A.B.; Zijlstra, B., P2: a random effects model with covariates for directed graphs, Stat. Neerl., 58, 234-254, (2004) · Zbl 1050.62117 [6] Dunbar, R., Neocortex size as a constraint on group size in primates, J. Hum. Evol., 22, 6, 469-493, (1992) [7] Frank, O.; Strauss, D., Markov graphs, J. Amer. Statist. Assoc., 81, 832-842, (1986) · Zbl 0607.05057 [8] Gladwell, M., The tipping point: how little things make a big difference, (2000), Little, Brown and Company [9] Goodreau, S., Advances in exponential random graph ($$p^\ast$$) models applied to a large social network, Social Networks, 29, 231-248, (2007) [10] Handcock, M. S.; Robins, G. L.; Snijders, T. A.B.; Moody, J.; Besag, J., Assessing degeneracy in statistical models of social networks, J. Amer. Statist. Assoc., 76, 33-50, (2003) [11] Hoff, P. D., Bilinear mixed effects models for dyadic data, J. Amer. Statist. Assoc., 100, 286-295, (2005) · Zbl 1117.62353 [12] Hoff, P., Modeling homophily and stochastic equivalence in symmetric relational data, (Advances in Neural Information Processing Systems. Vol. 20, (2008), MIT Press), 657-664 [13] Hoff, P. D.; Raftery, A. E.; Handcock, M. S., Latent space models for social networks analysis, J. Amer. Statist. Assoc., 97, 1090-1098, (2002) · Zbl 1041.62098 [14] Hunter, D. R.; Handcock, M. S., Inference in curved exponential family models for networks, J. Comput. Graph. Statist., 15, 565-583, (2006) [15] Kleinbaum, A. M., Organizational misfits and the origins of brokerage in intrafirm networks, Adm. Sci. Quart., 57, 407-452, (2012) [16] Langholz, B.; Goldstein, L., Conditional logistic analysis of case-control studies with complex sampling, Biostatistics (Oxford), 2, 1, 63-84, (2001) · Zbl 1017.62113 [17] Lewis, K.; Kaufman, J.; Gonzalez, M.; Wimmer, A.; Christakis, N., Tastes, ties, and time: a new social network dataset using facebook.com, Social Networks, 30, 330-342, (2008) [18] Michell, L.; Amos, A., Girls, pecking order and smoking, Soc. Sci. Med., 44, 1861-1869, (1997) [19] Neuhaus, J. M.; Jewell, N. P., The effect of retrospective sampling on binary regression models for clustered data, Biometrics, 46, 977-990, (1990) [20] Newman, M. E.J.; Girvan, M., Finding and evaluating community structure in networks, Phys. Rev. E, 69, (2004) [21] O’Malley, A. J.; Marsden, P. V., The analysis of social networks, Health Serv. Outcomes Res. Methodol., 8, 4, 222-269, (2008) [22] Paul, S.; O’Malley, A. J., Hierarchical longitudinal models of relationships in social networks, J. Roy. Statist. Soc. Ser. C, 62, 5, 705-722, (2013) [23] Pfeffermann, D.; Skinner, C. J.; Holmes, D. J.; Goldstein, H.; Rasbash, J., Weighting for unequal selection probabilities in multilevel models (disc: P41-56), J. R. Stat. Soc. Ser. B Stat. Methodol., 60, 23-40, (1998) · Zbl 0909.62006 [24] Raftery, A. E.; Niu, X.; Hoff, P. D.; Yeung, K., Fast inference for the latent space network model using a case-control approximate likelihood, J. Comput. Graph. Statist., 21, 4, 901-919, (2012) [25] Robins, G. L.; Snijders, T. A.B.; Wang, P.; Handcock, M. S.; Pattison, P. E., Recent developments in exponential random graph ($$p^\ast$$) models for social networks, Social Networks, 29, 2, 192-215, (2007) [26] Snijders, T.A.B., 2014. Description excerpt of 50 girls from “teenage friends and lifestyle study” data. http://www.stats.ox.ac.uk/ snijders/siena/s50_data.htm (accessed: 29.07.2014). [27] Spiegelhalter, D. J., Bayesian graphical modelling: a case-study in monitoring health outcomes, J. Roy. Statist. Soc. Ser. C, 47, 115-133, (1998) [28] van Duijn, M.; Snijders, T. A.B.; Zijlstra, B., P2: a random effects model with covariates for directed graphs, Stat. Neerl., 58, 234-254, (2004) · Zbl 1050.62117 [29] Wasserman, S.; Pattison, P., Logit models and logistic regressions for social networks: I. an introduction to Markov graphs and $$p^\ast$$, Psychometrika, 61, 401-425, (1996) · Zbl 0866.92029 [30] West, P., Sweeting, H., 1995. Background rationale and design of the west of scotland 11-16 study. Working Paper No. 52. Glasgow: MRC Medical Sociology Unit. [31] Zijlstra, B. J.H.; van Duijn, M.; Snijders, T. A.B., The multilevel p2 model: a random effects model for the analysis of multiple social networks, Methodology, 2, 42-47, (2006)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.