Files
Abstract
In this paper, it is shown how a mathematical program with equilibrium constraints (MPEC) can be used to estimate the parameters of a transportation model using an inconsistent set of observed prices and transportation costs. Supply and demand quantities in the markets are known but transport flows are unknown. The suggested methodology improves upon previous approaches as it avoids discarding valuable information in the process. Significant numerical problems with gradient solvers lead to the development of an algorithm that handles the specific structure of the employed optimization model. The stability and computational speed of this algorithm is tested and compared to alternative approaches using simulation techniques. The method is then successfully applied to a transportation model for agricultural crops for the country of Benin.