Weight Restrictions and Free Production in Data Envelopment Analysis

It is known that the incorporation of weight restrictions in models of data envelopment analysis may result in their infeasibility. In our paper we investigate this effect in detail. We show that the infeasibility is only one of several possible outcomes that point to a particular problem with weight restrictions. For example, the use of weight restrictions may also lead to zero or negative efficiency scores of some units. Removing problematic units from the data set does not necessarily remove the underlying problem caused by the weight restrictions and only makes it undetected. We prove that all such problems arise when weight restrictions induce free or unlimited production of outputs in the underlying technology. This is unacceptable from the production theory point of view and indicates that the weight restrictions need reassessing. We develop analytical criteria and computational methods that allow us to identify the above problematic situations.

[1]  Emmanuel Thanassoulis,et al.  Weights restrictions and value judgements in Data Envelopment Analysis: Evolution, development and future directions , 1997, Ann. Oper. Res..

[2]  B. Golany,et al.  Controlling Factor Weights in Data Envelopment Analysis , 1991 .

[3]  Abraham Charnes,et al.  Cone ratio data envelopment analysis and multi-objective programming , 1989 .

[4]  Harold O. Fried,et al.  The Measurement of Productive Efficiency and Productivity Growth , 2008 .

[5]  Victor V. Podinovski,et al.  DEA models for the explicit maximisation of relative efficiency , 2001, Eur. J. Oper. Res..

[6]  W. Cooper,et al.  Data Envelopment Analysis: A Comprehensive Text with Models, Applications, References and DEA-Solver Software , 1999 .

[7]  Victor V. Podinovski,et al.  Differential Characteristics of Efficient Frontiers in Data Envelopment Analysis , 2010, Oper. Res..

[8]  Lawrence M. Seiford,et al.  Data envelopment analysis (DEA) - Thirty years on , 2009, Eur. J. Oper. Res..

[9]  V. V. Podinovski Improving data envelopment analysis by the use of production trade-offs , 2007, J. Oper. Res. Soc..

[10]  V. V. Podinovski,et al.  The explicit role of weight bounds in models of data envelopment analysis , 2005, J. Oper. Res. Soc..

[11]  Ahti Salo,et al.  Ranking Intervals and Dominance Relations for Ratio-Based Efficiency Analysis , 2011, Manag. Sci..

[12]  Francisco Pedraja-Chaparro,et al.  On the Role of Weight Restrictions in Data Envelopment Analysis , 1997 .

[13]  R. Färe,et al.  The measurement of efficiency of production , 1985 .

[14]  Joe Zhu,et al.  CAR-DEA: Context-Dependent Assurance Regions in DEA , 2008, Oper. Res..

[15]  A. Charnes,et al.  Polyhedral Cone-Ratio DEA Models with an illustrative application to large commercial banks , 1990 .

[16]  Abraham Charnes,et al.  Measuring the efficiency of decision making units , 1978 .

[17]  R. Dyson,et al.  Reducing Weight Flexibility in Data Envelopment Analysis , 1988 .

[18]  Ronald W. Shephard,et al.  SEMI-HOMOGENEOUS PRODUCTION FUNCTIONS AND SCALING OF PRODUCTION , 1974 .

[19]  Emmanuel Thanassoulis,et al.  Introduction to the theory and application of data envelopment analysis , 2001 .

[20]  B. Golany,et al.  Alternate methods of treating factor weights in DEA , 1993 .

[21]  Emmanuel Thanassoulis,et al.  Data Envelopment Analysis:the mathematical programming approach to efficiency analysis , 2008 .

[22]  Cláudia S. Sarrico,et al.  Data Envelopment Analysis: A Comprehensive Text with Models, Applications, References and DEA-Solver Software , 2001, J. Oper. Res. Soc..

[23]  V. V. Podinovski,et al.  Production trade-offs and weight restrictions in data envelopment analysis , 2004, J. Oper. Res. Soc..

[24]  William W. Cooper,et al.  Handbook on data envelopment analysis , 2011 .

[25]  Russell G. Thompson,et al.  The role of multiplier bounds in efficiency analysis with application to Kansas farming , 1990 .

[26]  Pekka J. Korhonen,et al.  Restricting weights in value efficiency analysis , 2000, Eur. J. Oper. Res..