This article suggests that situations in which multiple research teams are convened under similar conditions present an opportunity to discover factors that lead to productive collaboration. It argues that social network analysis of research team outputs becomes more valuable when paired with data about research participant perceptions; and that any variables used as indicators of collaboration need to be calibrated using datasets from multiple studies with cross-team comparisons. The article provides an example of the kind of methodology needed to achieve this, describing a study with data from four research teams based at an Australian university campus, reporting their research performance over four years under conditions in which many variables were controlled and with results augmented by a survey of participant perceptions. Findings from the study indicate that there were exceptions to hypothesized associations between participant perceptions of collaboration and specific social network analysis measures over co-authorship data. The article suggests that, given the methodological challenges of studying research teams in the field, multiple datasets combining findings such as those in the present study are a path towards the development of indicators of productive higher education research collaboration.