Analiza paketa podatkov

Data Envelopment Analysis (DEA) is a decision making tool based on linear programming for measuring the relative efficiency of a set of comparable units. Besides the identification of relatively efficient and inefficient units, DEA identifies the sources and level of inefficiency for each of the inputs and outputs. This paper is a survey of the basic DEA models. A comparison of DEA models is given. The effect of model orientation (input or output) on the efficiency frontier and the effect of the convexity requirements on returns to scale are examined. The paper also explains how DEA models can be used to assess efficiency.Analiza paketa podatkov (DEA) je orodje za odločanje, ki za merjenje relativne učinkovitosti niza med seboj primerljivih enot uporablja linearno programiranje. Poleg iskanja relativno učinkovitih in neučinkovitih enot, DEA določa vzroke in nivo neučinkovitosti za vsak vhod in izhod. V prispevku je podan pregled osnovnih DEA modelov. Prikazana je primerjava DEA modelov. Preučili smo vpliv orientacije modela (vhod ali izhod) na mejo učinkovitosti in vpliv zahtev na skalo. Prispevek podaja tudi način, kako lahko DEA modele uporabimo za doseganje učinkovitosti