Simulating weights restrictions in data envelopment analysis by means of unobserved DMUs

Data envelopment analysis (DEA) is a method for assessing the comparative efficiencies of decision making units (e.g., banks and schools) by relating their output to their input levels, Restrictions are often imposed in these assessments to reflect prior judgments on the values of input and/or output variables. This paper introduces a new approach to capturing and using value judgments in DEA, based on unobserved Decision Making Units. In so doing, it opens up a whole new approach for reflecting value judgments in DEA assessments, which can offer advantages in certain situations.