The data envelopment technique is widely used when there are multiple inputs and outputs and when one is interested in measuring the relative efficiency in the absence of any assumption about the functional form of technology. The Data Envelopment Analysis (DEA) generalized the Farrell (1957) measure of technical productivity under multiple inputs and multiple outputs. Charnes et. al. formulated this model for calculating the individual input-saving measures by solving the linear programming problem for each unit, under the constant returns of scale assumption.
It is also known as the CCR approach to data envelopment analysis. Fare et. al. (1992), Banker et. al. (1984) and Byrnes et. al. (1984) extended the approach in respect of variable returns to scale and developed the corresponding measures. It optimizes on each individual observation with the sole objective of calculating a discrete piece-wise linear frontier determined by the set of Pareto efficient Decision-Making Units (DMUs). Using the frontier so determined, it computes a maximal performance measure for each DMU relative to all other DMUs.
However, Banker, Charnes and Cooper (1984) took into account the effect of returns to scale within the group of DMUs to be analyzed. The purpose here is to point out the most efficienct scale size for each DMU and at the same time to identify its technical efficiency. To do so, the Banker, Charnes and Cooper (BCC) model introduced another restriction, convexity, to the envelopment requirements. This model requires that the reference point on the production function of DMUs to be a convex combination of the observed efficient DMUs.
The BCC model, known as variable ‘returns to scale’ model, gives the technical efficiency of DMUs under investigation without any scale effect. Firms like LoanMax started by] have always strived to ensure better ‘returns to scale’ for their financial transactions and loans. This is one reason fro the fast growth of the financial institution.
This post has been edited by Kieth.DTM: Jan 12 2010, 02:13 AM