Dual Factor Role in Modeling of Data Envelopment Analysis

This paper develops a methodological framework for modelling and efficiency analysis by the use of Data Envelopment Analysis (DEA) technique. DEA finds the weights of inputs and outputs of the Decision-making unit(DMU) under consideration so that it gives an efficiency index by taking ratio of weighted sum of outputs to the weighted sum of inputs. An input is a quantity which is inversely affecting to the efficiency index and an output is a quantity which is directly affecting the efficiency index. The input and output weights are modelled so that they satisfy the non-negativity constraint. This efficiency index is used for discriminating among efficient and inefficient DMUs. Thus, tradition DEA requires discrete set of inputs and outputs. However, there may be cases where a parameter cannot be clearly categorized as input or output if initially it cannot be stated whether it will directly or inversely affect the efficiency index. Such parameters are termed as dual role factors. This paper tries to attempt a modelling approach towards this problem and proposes a methodological framework towards solving it.