Productivity Beliefs and Efficiency in Science

We develop a method to estimate producers' productivity beliefs when output quantities and input prices are unobservable, and we use it to evaluate the market for science. Our model of researchers' labor supply shows how their willingness to pay for inputs reveals their productivity beliefs. We estimate the model's parameters using data from a nationally representative survey of researchers and find the distribution of productivity to be very skewed. Our counterfactuals indicate that a more efficient allocation of the current budget could be worth billions of dollars. There are substantial gains from developing new ways of identifying talented scientists.