A dynamic model for the mutual constitution of individuals and events

Abstract We argue and show that a recently derived class of relational hyperevent models (RHEM) may be adopted to extend the sociological concept duality by linking it empirical data containing information on temporal order events. how RHEMs specified predict likelihood combinations individuals any size will jointly participate in future events, conditional their history participation past show, further, support hypothesis testing about competing mechanisms driving Finally, we used establish location events actually happened much larger space all possible could have happened, but did not. illustrate value using canonical dataset 18 women 14 time-ordered provide dynamic network visualizations link estimates model parameters qualitative insight dynamics mutual constitution While are also applicable large networks (e.g. coauthorship networks), small allows us examine greater detail model’s implications for each every observed event identify participant previous Scaling down our affords more detailed understanding between quantitative results expressed as parameter estimates, features original observations.