Learning When to Quit: An Empirical Model of Experimentation in Standards Development

Using data from the Internet Engineering Task Force (IETF), a voluntary organization that develops protocols for managing internet infrastructure, we estimate a dynamic discrete choice model of the decision to continue or abandon a line of research. The model's key parameters measure the speed at which authors learn whether their project will become a technology standard. We use the model to simulate two innovation policies: an R&D subsidy and a publication prize. While subsidies have a larger impact on research output, the optimal policy depends on the level of R&D spillovers. (JEL D83, L86, O31, O38)