作者: Rolf Färe , Carlos Martins-Filho , Michael Vardanyan
DOI: 10.1007/S11123-009-0164-4
关键词:
摘要: The introduction of directional distance functions has given researchers an alternative to Shephard functions. In this paper we conduct a Monte Carlo study investigate the performance as approximation for models technology. Our results indicate that quadratic representations technology have better properties than translog parameterizations.