Using the Positive Mathematical Programming Method to Calibrate Linear Programming Models

Wien

2005

11 S.

Bandaufführung

13194

121024

In agricultural economics, several calibration and aggregation approaches have evolved in mathematical programming models. This article combines in a linear programming model features of the Positive Mathematical Programming method with an aggregation approach that is constrained to the production possibility set spanned by a convex combination of observed production activities. The combination is obtained by using a variable separation technique that approximates a non-linear objective function. Therefore, linear programming models can be exactly calibrated to observed production activities. The aggregation of production activities in homogenous production response units assumes that farmers in a region are treated such as they respond in the same way. Both methodologies are embedded in economic reasoning and provide a robust framework to solve large-scale linear programming models in reasonable time.