Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
We present new identification results for stochastic sequential bargaining models when the data only reports the time of agreement and the evolution of observable states. With no information on the stochastic surplus available for allocation or how it is allocated under agreement, we recover the latent surplus process, the distribution of unobservable states, and the equilibrium outcome in counterfactual contexts. The method we propose, which is constructive and original, can also be adapted to establish identification in general optimal stopping models.