Nonparametric Production Technologies with Multiple Component Processes
提出一种新的非参数方法，用于评估具有多个组件过程的决策单元效率，允许组件特定和共享的投入产出，无需分配信息，并在中学教育和蒙特卡洛模拟中验证了有效性。
We develop a nonparametric methodology for assessing the efficiency of decision-making units operating in a production technology with several component processes. The latter is modeled by the new multiple hybrid returns-to-scale (MHRS) technology, formally derived from an explicitly stated set of production axioms. In contrast with the existing models of data envelopment analysis (DEA), the MHRS technology allows the incorporation of component-specific and shared inputs and outputs that represent several proportional (scalable) component production processes as well as nonproportional inputs and outputs. Our approach does not require information about the allocation of shared inputs and outputs to component processes or any assumptions about this allocation. We demonstrate the usefulness of the suggested approach in an application in the context of secondary education and also in a Monte Carlo study based on a simulated data generating process.