Undesirable specialization in the construction of composite policy indicators: The Environmental Performance Index

The non-parametric Data Envelopment Analysis approach is increasingly used to construct composite indicators for country performance monitoring, benchmarking, and policy evaluation in a large variety of fields. The flexibility in the definition of aggregation weights is praised as the method's most important advantage: DEA allows each evaluated country to look for its own optimal weights that maximize the composite indicator relative to the other countries. However, this flexibility also carries a potential disadvantage as it may allow countries to appear as a brilliant performer in a manner that is hard to justify: by ignoring or overemphasizing one or multiple of the judiciously selected performance indicators. To illustrate this issue of undesirable specialization in DEA-based evaluations, this paper compares the Environmental Performance Index (EPI) as computed by the optimistic and pessimistic version of the DEA-model as proposed by Zhou et al. (2007). Based on both computed composites, undesirable specialization in performance is identified.

[1]  Kaoru Tone,et al.  A comparative site evaluation study for relocating Japanese government agencies out of Tokyo , 2003 .

[2]  A. Charnes,et al.  Constrained game formulations and interpretations for data envelopment analysis , 1989 .

[3]  M. Hopkins.  Human development revisited: A new UNDP report , 1991 .

[4]  John E. Beasley,et al.  Restricting Weight Flexibility in Data Envelopment Analysis , 1990 .

[5]  Rolf Färe,et al.  An Economic Approach to Achievement and Improvement Indexes , 2001 .

[6]  Saurabh Gupta,et al.  An overview of sustainability assessment methodologies , 2009 .

[7]  Jian-Bo Yang,et al.  Measuring the performances of decision-making units using geometric average efficiency , 2007, J. Oper. Res. Soc..

[8]  Nikolaos A. Skondras,et al.  Application and assessment of the Environmental Vulnerability Index in Greece , 2011 .

[9]  Shinji Kaneko,et al.  Dynamic sustainability assessment of countries at the macro level: A principal component analysis , 2011 .

[10]  A. K. Dikshit,et al.  Development of composite sustainability performance index for steel industry , 2007 .

[11]  Earl R. Babbie,et al.  The practice of social research , 1969 .

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

[13]  Laurens Cherchye,et al.  Creating composite indicators with DEA and robustness analysis: the case of the Technology Achievement Index , 2006, J. Oper. Res. Soc..

[14]  Hans Bjurek,et al.  Benchmarking European labour market performance with efficiency frontier techniques , 2000 .

[15]  C. A. K. Lovell,et al.  Using Fieldwork, GIS and DEA to Guide Management of Urban Stream Health , 2013 .

[16]  Willem Moesen,et al.  Towards a synthetic indicator of macroeconomic performance: Unequal weighting when limited information is available , 1991 .

[17]  D. Jahn.  Environmental performance and policy regimes: Explaining variations in 18 OECD-countries , 1998 .

[18]  Joe Zhu,et al.  A buyer-seller game model for selection and negotiation of purchasing bids: Extensions and new models , 2004, Eur. J. Oper. Res..

[19]  Measuring the quality of life in European Union , 2003 .

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

[21]  Jian-Bo Yang,et al.  Failure mode and effects analysis by data envelopment analysis , 2009, Decis. Support Syst..

[22]  M. Farrell.  The Measurement of Productive Efficiency , 1957 .

[23]  Stefano Tarantola,et al.  Handbook on Constructing Composite Indicators: Methodology and User Guide , 2005 .

[24]  Laurens Cherchye,et al.  An Introduction to ‘Benefit of the Doubt’ Composite Indicators , 2007 .

[25]  R. Banker.  A game theoretic approach to measuring efficiency , 1980 .

[26]  B. W. Ang,et al.  A mathematical programming approach to constructing composite indicators , 2007 .