Social network research focuses on the study of social systems by conceptualizing their internal structure in terms of sets of complex dependencies among social agents in the form of dyadic social ties. Typically, models for social networks incorporate additional features such as actor attributes. Models for social networks may also be extended in various ways by considering, for example, multiplex or bipartite representations. However, incorrect inferences can be drawn from social network analysis if the system is conceptualized in an overly simplistic way. This can happen if crucial elements of social structure are ignored when the data are collected, or are mis-specified in the model used for the analysis. As social network researchers, we know this well, because we avoid individualistic analysis of attributes when social structure is relevant. In one of the foundational articles of contemporary social network analysis, Harrison White and co-authors warned against relying on social classification as the sole basis for understanding social structure: “. . .largely categorical descriptions of social structure have no solid theoretical grounding; . . . network concepts may provide the only way to construct a theory of social structure” (White et al., 1976, p.732). Network researchers (but not all social scientists) have learnt that lesson well.