Abstract
We present a novel Data Envelopment Analysis (DEA)-type method to evaluate the productive efficiency of Decision Making Units (DMUs) when the empirical analyst has incomplete output information. Our method builds on the Afriat Theorem that was originally proposed in the context of consumer analysis. We translate this result to a production setting and show that it provides a productive basis for cost efficiency analysis in the absence of output information. Our method is versatile in that it can accommodate a continuum of instances characterized by incomplete information on output quantities. We illustrate its practical usefulness through an empirical application that evaluates the productive efficiency performance of countries in producing national welfare.
Similar content being viewed by others
Notes
In what follows, complete output information refers to situations where the DMUs’ output levels are fully observed, whereas incomplete output information refers to situations where these output levels are imprecisely observed. In an extreme scenario, incomplete output information boils down to fully unobserved output (see Sections 2.1 and 2.2). We will refer to an intermediate scenario (with some observable information on the output levels) as characterized by “partial” output information (see Section 2.3).
In this respect, we refer to Afriat (1972), Hanoch and Rothschild (1972), Diewert and Parkan (1983) and Varian (1984) for seminal contributions on the nonparametric approach to analyzing producer behavior. Similar to the current paper, these studies also build on the formal analogy between the analysis of consumer and producer behavior. Next, Banker and Maindiratta (1988) provide an early study on the close connection between the nonparametric approach to production analysis and DEA. Importantly, these earlier studies all assume complete output information in the sense that the DMUs’ output levels are fully observed. As motivated above, the main contribution of the current study is that we present tools for analyzing productive efficiency in the absence of such complete output information.
This use of most favorable output orderings reflects the “Benefit of the Doubt” (BoD) interpretation of DEA efficiency analysis. See, for example, Cherchye et al. (2007) and, more recently, Färe and Karagiannis (2014) for detailed discussions of this BoD interpretation of DEA. Whereas this BoD interpretation usually refers to the (unknown) weights that are used for aggregating the inputs and outputs in the DEA efficiency measures, we apply in our setting this BoD principle to the (unknown) output orderings that are used in the efficiency evaluation.
See the Appendix for a list of the countries that we consider. We have cleaned the original data to prevent that our empirical results are severely affected by extreme outliers and noise. To construct Wage we make use of nominal GDP. We obtain output-side nominal GDP by multiplying output-side real GDP by its price level. Given the presence of outliers in the latter, we winsorize it at the 5th and 95th percentile of all observations in the PWT 10.0 data set. We set the average usage cost of capital equal to 0.15, following Gilchrist and Zakrajsek (2007). To avoid potential influences from outliers in the input price data, we winsorize Wage and Capital usage price at the 10th and 90th percentile of all observations in the PWT 10.0 data set. Further, we drop observations with a labor share or a capital share above 1. Last, we drop observations with missing values for the variables under consideration (Real GDP, L, K, Wage, Capital usage price), and limit our analysis to countries for which we have data on all these variables for the years 1990, 2000, 2010, and 2019.
Consistent with our main analysis above, for α > 1.5 we obtain very high average efficiency scores and low standard deviations. These results are available upon request.
Specifically, Kumar and Russell (2002) originally analyzed a sample with 57 countries. We have complete information on the variables under study for the four time periods under consideration for 50 of these 57 countries.
References
Afriat SN (1967) The construction of utility functions from expenditure data. International Economic Review 8(1):67–77
Afriat SN (1972) Efficiency estimation of production functions. International Economic Review 13(3):568–598
Badunenko, O, Henderson, DJ, Zelenyuk, V, et al. (2017). The productivity of nations. Emili Grifell-Tatjé, CKL and C. Sickles, R., editors, The Oxford Handbook of Productivity Analysis.
Banker RD, Maindiratta A (1988) Nonparametric analysis of technical and allocative efficiencies in production Econometrica. 56(6):1315–1332
Cazals C, Florens J-P, Simar L (2002) Nonparametric frontier estimation: a robust approach. Journal of Econometrics 106(1):1–25
Cherchye L, Moesen W, Rogge N, Puyenbroeck TV (2007) An introduction to ‘benefit of the doubt’composite indicators. Social Indicators Research 82:111–145
Cherchye L, De Rock B, Dierynck B, Roodhooft F, Sabbe J (2013) Opening the “black box” of efficiency measurement: Input allocation in multioutput settings. Operations Research 61(5):1148–1165
Cherchye L, Demuynck T, De Rock B, De Witte K (2014) Non-parametric analysis of multi-output production with joint inputs. The Economic Journal 124(577):735–775
Cherchye L, Demuynck T, De Rock B, Hjertstrand P (2015) Revealed preference tests for weak separability: an integer programming approach. Journal of Econometrics 186(1):129–141
Cherchye, L, De Rock, B, Saelens, D, Verschelde, M and Roets, B (2021a). Efficiency analysis with unobserved inputs: An application to endogenous automation in railway traffic management. Available at SSRN 3820457.
Cherchye, L, Demuynck, T, De Rock, B, Duprez, C, Magerman, G and Verschelde, M. (2021b). Structural identification of productivity under biased technological change. ECARES Working Paper Series 2021-28, ULB – Université Libre de Bruxelles.
Daraio C, Simar L (2005) Introducing environmental variables in nonparametric frontier models: a probabilistic approach. Journal of Productivity Analysis 24:93–121
Diewert WE (1973) Afriat and revealed preference theory. The Review of Economic Studies 40(3):419–425
Diewert WE (1980) Capital and the theory of productivity measurement. American Economic Review 70(2):260–267
Diewert, WE, Parkan, C (1983). Linear programming tests of regularity conditions for production functions. In Quantitative studies on production and prices, pages 131–158. Springer.
Färe R, Grosskopf S (1995) Nonparametric tests of regularity, farrell efficiency, and goodness-of-fit. Journal of Econometrics 2(69):415–425
Färe R, Karagiannis G (2014) Benefit-of-the-doubt aggregation and the diet problem. Omega 47:33–35
Färe R, Zelenyuk V (2021) On aggregation of multi-factor productivity indexes. Journal of Productivity Analysis 55:107–133
Färe R, Grosskopf S, Norris M, Zhang Z (1994) Productivity growth, technical progress, and efficiency change in industrialized countries. American Economic Review 84(1):66–83
Farrell MJ (1957) The measurement of productive efficiency. Journal of the Royal Statistical Society: Series A (General) 120(3):253–281
Feenstra RC, Inklaar R, Timmer MP (2015) The next generation of the penn world table. American Economic Review 105(10):3150–82
Fleurbaey M (2009) Beyond GDP: The quest for a measure of social welfare. Journal of Economic Literature 47(4):1029–1075
Gilchrist, S and Zakrajsek, E (2007). Investment and the cost of capital: New evidence from the corporate bond market. National Bureau of Economic Research Working Paper No. w13174.
Gouma, R and Inklaar, R (2021). Comparing productivity growth across databases. Ggdc research memorandum no. 193, University of Groningen.
Hanoch G, Rothschild M (1972) Testing the assumptions of production theory: a nonparametric approach. Journal of Political Economy 80(2):256–275
Henderson DJ, Russell RR (2005) Human capital and convergence: a production-frontier approach. International Economic Review 46(4):1167–1205
Kumar S, Russell RR (2002) Technological change, technological catch-up, and capital deepening: relative contributions to growth and convergence. American Economic Review 92(3):527–548
Meng Y, Parmeter CF, Zelenyuk V (2023) Is newer always better? A reinvestigation of productivity dynamics using updated pwt data. Journal of Productivity Analysis 59(1):1–13
Saelens, D. (2023). Nonparametric efficiency analysis with unobserved inputs in multi-output settings. FEB Research Report Department of Economics.
Shephard, R. W. (1953). Cost and production functions. Princeton University Press.
Talla Nobibon F, Cherchye L, Crama Y, Demuynck T, De Rock B, Spieksma FC (2016) Revealed preference tests of collectively rational consumption behavior: formulations and algorithms. Operations Research 64(6):1197–1216
Varian HR (1982) The nonparametric approach to demand analysis. Econometrica 50(4):945–973
Varian HR (1984) The nonparametric approach to production analysis. Econometrica 52(4):579–597
Varian HR (1990) Goodness-of-fit in optimizing models. Journal of Econometrics 46(1-2):125–140
Zhu, J. (2015). Data Envelopment Analysis a Handbook of Models and Methods. Springer.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The author declares no competing interests.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix: list of countries used in the empirical application
Appendix: list of countries used in the empirical application
Angola, Argentina, Armenia, Australia, Austria, Azerbaijan, Bahamas, Bahrain, Barbados, Belgium, Benin, Bolivia (Plurinational State of), Bosnia and Herzegovina,Botswana, Brazil, Bulgaria, Burkina Faso, Cabo Verde, Cameroon, Canada, Chile, China, Hong Kong SAR, China, Macao SAR, Colombia, Costa Rica, Croatia, Cyprus, Czech Republic, CÔte d’Ivoire, Denmark, Djibouti, Dominican Republic, Ecuador, Egypt, Estonia, Eswatini, Fiji, Finland, France, Gabon, Germany, Greece, Guatemala, Guinea, Honduras, Hungary, Iceland, India, Indonesia, Iran (Islamic Republic of), Iraq, Ireland, Israel, Italy, Jamaica, Japan, Jordan, Kenya, Kuwait, Kyrgyzstan, Latvia, Lebanon, Lesotho, Lithuania, Luxembourg, Malaysia, Malta, Mauritius, Mexico, Morocco, Namibia, Netherlands, New Zealand, Nicaragua, North Macedonia, Norway, Oman, Panama, Paraguay, Peru, Philippines, Poland, Portugal, Qatar, Republic of Korea, Romania, Rwanda, Sao Tome and Principe, Saudi Arabia, Senegal, Singapore, Slovakia, Slovenia, South Africa, Spain, Sri Lanka, Sudan, Suriname, Sweden, Switzerland, Taiwan, Thailand, Togo, Trinidad and Tobago, Tunisia, Turkey, United Kingdom, United States, Uruguay, Uzbekistan and Zimbabwe.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Cherchye, L., De Rock, B., Saelens, D. et al. Productive efficiency analysis with incomplete output information. J Prod Anal (2023). https://doi.org/10.1007/s11123-023-00697-w
Accepted:
Published:
DOI: https://doi.org/10.1007/s11123-023-00697-w