Abstract
Research into missing network data is growing, with a focus on the impact of missing ties on network statistics or network model parameters. Longitudinal network studies using stochastic actor-oriented models (SAOMs) focus on the co-evolution of network structure and behavior/attributes to disentangle influence and selection mechanisms. Still little is known about the impact of missing behavior data on estimated effect parameters in SAOMs. This paper examines seven different methods that are currently available to deal with missing behavior data: complete cases, three single imputation procedures (imputing the mean, random hot deck, nearest neighbor hot deck), one multiple imputation procedure (based on predictive mean matching), and two methods available in the RSIENA software to estimate SAOMs (default method based on imputation and available cases, and a method based on dummy variables). In a simulation study based on four real-life data sets, the impact of these methods on estimated parameters of SAOMS was investigated. Missing behavior data were created under different conditions (proportions, mechanisms), and the missing data methods were used to estimate SAOMs on the incomplete data. The effect of the missing data methods was inspected using three criteria: model convergence, parameter bias, and parameter coverage. The results show that, in general, the default method available in the RSIENA software gives the best outcomes for all three criteria. The dummy-based method generally performed worse than the default method, as did the imputation procedures. The multiple imputation procedure sometimes outperformed the single imputations and the three single imputation methods often gave the same results. The effects of missing data mechanism and data set were small.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Notes
Often a fourth class of treatments is distinguished, i.e., (re)weighting procedures, which are not considered for missing network data.
References
Adams J, Schaefer DR (2018) Visualizing stochastic actor-based model microsteps. Sociol Res Dyn World, 4, 1–3
Allison PD (2001) Missing data. (Sage University papers series on quantitative applications in the social sciences), 07–136. Thousand Oaks:Sage
Borgatti SP, Molina JL (2003) Ethical and strategic issues in organizational social network analysis. J Appl Behav Sci 39:337–349
Burt RS (1987) A note on missing network data in the general social survey. Soc Netw 9:63–73
Costenbader E, Valente TW (2003) The stability of centrality measures when networks are sampled. Soc Netw 25:283–307
de la Haye K, Embree J, Punkay M, Espelage DL, Tucker JS, Green HD (2017) Analytic strategies for longitudinal networks with missing data. Soc Netw 50:17–25
Floyd SW, Wooldridge B (1997) Middle management’s strategic influence and organizational performance. J Manag Stud 34(3):465–485
Handcock MS, Gile KJ (2010) Modeling social networks from sampled data. Ann Appl Stat 4:5–25
Hipp JR, Wang C, Butts CT, Jose R, Lakon CM (2015) Research note: the consequences of different methods for handling missing network data in stochastic actor based models. Soc Netw 41:56–71
Huisman M (2009) Imputation of missing network data: some simple procedures. J Soc Struct 10:1–29
Huisman M, Krause RW (2017) Imputation of missing network data. In: Alhajj R, Rokne J (eds) Encyclopedia of social network analysis and mining. Springer, New York. (https://doi.org/10.1007/978-1-4614-7163-9_394-1)
Huisman M, Steglich CEG (2008) Treatment of non-response in longitudinal network studies. Soc Netw 30:297–308
Huitsing G, van Duijn MAJ, Snijders TAB, Perren S, Veenstra R (2014) Self-, peer-, and teacher reports on bullying networks in kindergartens. In: Huitsing G. A social network perspective on bullying. ICS-dissertation, Groningen
Koskinen JH, Robins GL, Pattison PE (2010) Analyzing exponential random graph (p-star) models with missing data using Bayesian data augmentation. Stat Method 7:366–384
Koskinen JH, Robins GL, Wang P, Pattison PE (2013) Bayesian analysis for partially observed network data, missing ties, attributes and actors. Soc Netw 35:514–527
Kossinets G (2006) Effects of missing data in social networks. Soc Netw 28:247–268
Krause RW, Huisman M, Snijders TAB (2018a) Multiple imputation for longitudinal network data. Ital J Appl Stat 30:33–57
Krause RW, Huisman M, Steglich CEG, Snijders TAB (2018b) Missing network data: a comparison of different imputation methods. In: Proceedings of the 2018 IEEE/ACM international conference on advances in social networks analysis and mining
Little RJA (1988) Missing data adjustments in large surveys. J Bus Econ 6:287–301
Michell L, Amos A (1997) Girls, pecking order and smoking. Soc Sci Med 44(12):1861–1869
Ouzienko V, Obradovic Z (2014) Imputation of missing links and attributes in longitudinal social surveys. Mach Learn 95:329–356
Pearson M, West P (2003) Drift Smoke Rings Connect 25(2):59–76
Ripley RM, Snijders TAB, Boda Z, Vörös A, Preciado P (2017) Manual for SIENA version 4.0 (version September 9, 2017). University of Oxford, Department of Statistics, Nuffield College, Oxford. http://www.stats.ox.ac.uk/siena/
Robins G, Pattison P, Woolcock J (2004) Missing data in networks: exponential random graph (p*) models for networks with non-respondents. Soc Netw 26:257–283
Rubin DB (1976) Inference and missing data. Biometrika 63:581–592
Rubin DB (1987) Multiple imputation for nonresponse in surveys. Wiley, New York
Schafer JL, Graham JW (2002) Missing data: our view of the state of the art. Psychol Methods 7:147–177
Smith JA, Moody J (2013) Structural effects of network sampling coverage I: nodes missing at random. Soc Netw 35:652–668
Smith JA, Moody J, Morgan JH (2017) Network sampling coverage II: the effect of non-random missing data on network measurement. Soc Netw 48:78–99
Snijders TAB (2001) The statistical evaluation of social network dynamics. Sociol Methodol 31:361–395
Snijders TAB (2005) Models for longitudinal network data. In: Carrington PJ, Scott J, Wasserman S (eds) Models and methods in social network analysis. Cambridge University Press, Cambridge, pp 215–247
Snijders TAB (2017) Stochastic actor-oriented models for network dynamics. Annu Rev Stat Appl 4:343–363
Snijders TAB, Koskinen JH, Schweinberger M (2010a) Maximum likelihood estimation for social network dynamics. Ann Appl Stat 4:567–588
Snijders TAB, van de Bunt GG, Steglich CEG (2010b) Introduction to actor-based models for network dynamics. Soc Netw 32:44–60
Stork D, Richards WD (1992) Nonrespondents in communication network studies. Group Org Manag 17:193–209
van Buuren S (2012) Flexible imputation of missing data. Chapman & Hall/CRC, Boca Raton
Van Buuren S, Groothuis-Oudshoorn K (2011) mice: multivariate imputation by chained equations in R. J Stat Softw 45:1–67
Veenstra R, Dijkstra JK, Steglich C, Van Zalk MH (2013) Network–behavior dynamics. J Res Adolesc 23(3):399–412
Wang C, Butts CT, Hipp JR, Jose R, Lakon CM (2016) Multiple imputation for missing edge data: a predictive evaluation method with application to add health. Soc Netw 45:89–98
Whitmeyer JM, Wittek R (2010) Inequalities in network structures. Soc Sci Res 39(1):152–164
Zandberg T, Huisman M, Wittek R (2018) Middle manager’s innovative work behavior in a multi-site organization: the influence of social network, spatial distance and organizational complexity. (Unpublished manuscript)
Žnidaršič A, Ferligoj A, Doreian P (2012) Non-response in social networks: the impact of different non-response treatments on the stability of blockmodels. Soc Netw 34:438–450
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zandberg, T., Huisman, M. Missing behavior data in longitudinal network studies: the impact of treatment methods on estimated effect parameters in stochastic actor oriented models. Soc. Netw. Anal. Min. 9, 8 (2019). https://doi.org/10.1007/s13278-019-0553-2
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s13278-019-0553-2