We develop a novel probabilistic model for interpersonal coordination as alatent phenomenon explaining statistical temporal influence between multiplecomponents in a system. For example, the state of one person can influence thatof another at a later time, as indicated by their observed behaviors. Wecharacterize coordination as the degree to which the distributions for such statesat one time point are merged for the next salient time point. We evaluate ourmodel in the context of three-person teams executing a virtual search and rescue(SAR) mission. We first use synthetic data to confirm that our technicaldefinition of coordination is consistent with expectations and that we canrecover generated coordination despite noise. We then show that capturedcoordination can be predictive of team performance on real data. Here we usespeech vocalics and semantics to infer coordination for 36 teams carrying out twosuccessive SAR missions. In two different datasets, we find that coordinationis generally predictive of team score for the second mission, but not for thefirst, where teams are largelylearning to play the game. In addition, we found that including a semantic modality improves prediction in some scenarios. This shows that our intuitive technical definitioncan capture useful explanatory aspects of team behavior.