Imputation of missing network data:Some simple procedures

Analysis of social network data is often hampered by non-response and missingdata. Recent studies show the negative effects of missing actors and ties on thestructural properties of social networks. This means that the results of socialnetwork analyses can be severely biased if missing ties were ignored and onlycomplete cases were analyzed. To overcome the problems created by missingdata, several treatment methods are proposed in the literature: model-basedmethods within the framework of exponential random graph models, and im-putation methods. In this paper we focus on the latter group of methods, andinvestigate the use of some simple imputation procedures to handle missingnetwork data. The results of a simulation study show that ignoring the missingdata can have large negative effects on structural properties of the network.Missing data treatment based on simple imputation procedures, however, doesalso have large negative effects and simple imputations can only successfullycorrect for non-response in a few specific situations