AN IMPROVED APPROACH FOR MEASUREMENT EFFICIENCY OF DEA AND ITS STABILITY USING LOCAL VARIATIONS

This paper developed an improved sensitivity analysis approach in the efficient Decision-Making Units (DMUs) when the data uncertainty occured locally. This analysis consider the stability of an efficient DMU by deteriorating a class of DMUs simultaneously in the same directions to keep the test DMU remains on the efficient frontier. The new approach generalizes the usual DEA sensitivity analysis in which the data variations are considered either on the single test DMU or on the all over DMUs. This enables the decision maker to take suitable actions that meet the possible local variations