Integrating risk and uncertainty in PMP models

Positive Mathematical Programming (PMP) is one of the most commonly used methods of calibrating activity linear programming (LP) models in agriculture. PMP applications published thus far focus on the estimation of a farm’s nonlinear cost or profit function and rely on the recovery of unobserved or implicit information that can explain the initial model’s inability to calibrate. In this paper we use the PMP procedure to calibrate an expected utility model under the assumption that this implicit information can reveal a farmer’s profit expectations and risk attitude. The perfect calibration shows that PMP can be applied not only to LP models, but also to models that incorporate risk and this provides an interesting alternative to the traditional PMP methodology.