A Stochastic Frontier Model with an Effect Stochastic Frontier Models with Endogenous Selection

Government policies are frequently used throughout the world to promote productivity. Some of the policies are designed to enhance production technology, and others are meant to improve production efficiency. In addition, another issue to consider in designing and evaluating policies is whether a mediator is required/effective in achieving the final outcome. To better understand and evaluate the policies, we propose a new stochastic frontier model with a treatment status and a mediator, both of which are allowed to be endogenous. The model allows us to decompose the total program (treatment) effect into the technology and efficiency components, and it also allows us to investigate whether the effect takes place directly from the program or indirectly through a particular mediator. We illustrate the empirical application of the model using data for India to study the effects of large dams on the local districts’ agricultural production.