COST EFFICIENCY IN REGIONAL BUS COMPANIES: AN APPLICATION OF ALTERNATIVE STOCHASTIC FRONTIER MODELS *

摘要: As the Swiss government seeks to reorganize regional bus services and put operation of lines out for public bid, benchmarking methods are needed evaluate bids requested subsidies adjust minimum win operating rights. That is done by comparing individual operators "best" observed practice, but do so accurately, it necessary separate exogenous factors that could contribute higher costs from operators' inherent efficiencies. The purpose this study analyze different panel data frontier models in terms their ability make distinction. In sample studied, Greene's "true" random effects model demonstrates a considerable advantage over other separating heterogeneous innate inefficiencies. Models not have tend overestimate inefficiencies operators. be valuable setting benchmark regulating network industries, though care must taken account cost pressures structures unique each industry unaccounted mechanical use model.