Collaboration in Bipartite Networks

This paper proposes a general framework for studying the impact of collaboration on team production. First, we build a micro-founded model for team production, where collaboration between agents is represented by a bipartite network. The Nash equilibrium of the game incorporates both the complementarity effect between collaborating agents and the substitutability effect between concurrent projects of the same agent. Next, we propose a Bayesian MCMC procedure to estimate the structural parameters, taking into account the endogenous participation of agents in projects. We then illustrate the empirical relevance of the model by analyzing the collaboration network of inventors in the semiconductor and pharmaceutical industries. We find that the estimated complementarity and substitutability effects are both positive and significant when the endogenous matching between inventors and patents is controlled for, and are downward biased otherwise. To show the importance of correctly estimating the structural model for policy analysis, we conduct a counterfactual study for an innovation incentive program. We find that the effectiveness of the innovation incentive tends to be understated when the complementarity effect is ignored and overstated when the substitutability effect is ignored. Moreover, we find that the higher the complementarity effect, the more effective the program. We also derive the optimal incentive scheme and show that there is substantial improvement in patent innovations under the optimal incentive scheme.