Stochastic Data Envelopment Analysis (DEA) in measuring the efficiency of dairy farms in Hungary

Abstract

Dairy enterprise is a very risky activity: the profitability of the enterprise is affected by the fluctuation of feed and animal health products prices from inputs, and by the fluctuation of end-product prices. Under these circumstances it is essential for the cattle breeders, in order to survive, to harness the reserves in management as effectively as possible. In our research we analysed the efficiency and risk of some dairy farms by applying classical Data Envelopment Analysis (DEA) and stochastic DEA models. The choice of this method is justified by the fact that there was not such an available reliable database by which production functions could have been defined, and DEA makes possible to manage simultaneously some inputs and outputs, i.e. complex decision problems. By using DEA, the sources that cause shortfall on the inefficient farms can be identified, analysed and quantified, so the corporate decision support can be supported successfully. A disadvantage of the classical DEA model is that the stochastic factors of farming cannot be treated either on the side of inputs or outputs; therefore their results can be adopted with reservations, especially in agricultural models. It may have been because of that we could meet not so many agricultural applications so far. Considering the price of inputs and outputs as probability variables we have done 1000 simulation runs in our research. As results, it can be stated that at which intervals of the input and output factors can become competitive and the fluctuation of these factors can cause what level of risk at each farm.