Evaluating and ranking decision making units in the two-stage network
DEA based on reference frontier
Abstract
The present study proposes a method for evaluating and ranking the
efficiency of decision-making units (DMUs) that has a two-stage network
structure in data envelopment analysis (DEA). Measuring the efficiency
of two-stage network systems in data envelopment analysis has developed
considerably, but ranking it in a logical and accurate analysis is a
subject that still needs further study. In the present study, a model is
presented that can consider the impact of each efficient DMUs on the
whole two-stage network system, as well as using the reference frontier,
the impact of each efficient DMUs in each evaluating non-efficient DMUs.
It also provided more information to rank and identify the impact of
extreme efficient DMUs on non-efficient DMUs by reference frontier. The
concept of reference frontier introduced in the present study has the
potential to determine the contribution of each extreme efficient DMUs
in constructing a reference frontier for each non-extreme efficient DMUs
and non-efficient DMUs. These facts have been investigated using logical
reasoning and proof of several theorems, and have been discussed with a
Practical example.