Abstract
This paper provides a new method to define a Euclidean common set of weights (ECSW) in data development analysis (DEA) that (1) allows ranking both efficient and inefficient firms, (2) is more realistic in terms of determination of weights, and (3) generates rankings for banks consistent with their credit ratings. We first use DEA to determine the efficient frontier and then estimate a common set of weights that can minimize the Euclidean distance between the firms and that frontier. This process is illustrated by a simple numerical example and is extended to a real-life situation using the Eurozone banking sector. Our ECSW approach outperforms other common set of weights approaches in both numerical and real-life examples, and in terms of providing rankings consistent with banks’ credit ratings.
Similar content being viewed by others
Notes
The first two methods deal with weight restriction (because the weights for individual inputs or outputs for DMUs can be very low, allowing those inputs or outputs to be effectively ignored) and thus require additional information. The last two do not and thus are more appropriate within the general DEA context.
Mathematically, a norm is a total size or length of all vectors in a vector space or matrices. Hence, the L1 norm is defined as the sum of the absolute values of its components, and the L2 norm is the square root of the sum of the squares of the absolute values of its components. Meanwhile, the L∞ norm is defined as the maximum of the absolute values of its components (Horn and Johnson 2012).
Additionally, the L1 norm, also known as “city block” or Manhattan distance, is not the shortest distance between two points, in comparison to the Euclidean geometric distance of the L2 norm.
This approach was also used in Wang et al. (2011), although they referred to it as a regression analysis.
Although there is a constraint requiring the efficiency scores of other DMUs using that set of weights to also have to be less than or equal to one—see Eq. (1).
In DEA, there must be at least one efficient DMU that lies on the frontier with efficiency score equal to one.
If \( p = 1 \), we have D1 as the “city block” or Manhattan measure of distance (L1 norm). If \( p = 2 \), we have D2 as the Euclidean distance measure (L2 norm). And if \( p = \infty \), we have D∞ as the Chebyshev distance (L∞ norm).
Wang et al. (2011) also used the L2 norm distance in calculating their CSW, although they called it the regression analysis method (RAM).
DEA can only rank inefficient DMUs whilst super-efficiency DEA (Andersen and Petersen 1993) can rank efficient DMUs; they thus both belong to the DSW approach. The LP2008 approach is therefore only focused on ranking efficient DMUs.
\( \Delta_{j}^{O} \) and \( \Delta_{j}^{I} \) are identical to ∆Y and ∆X in Fig. 1 (Panel B), respectively. Notice that this (artificial) virtual position lies on the slope 1.0 frontier, and thus has the characteristic of equal value in both coordinates, i.e. x = y. Consequently, the (absolute value) of the gaps should be equal as well, i.e. \( \left| {\Delta_{j}^{O} } \right| = \left| {\Delta_{j}^{I} } \right| \). This position, therefore, may not identical with the (optimal) virtual position using the DSW.
Ramezani-Tarkhorani et al. (2014) argued that the second criteria should be achieved by comparing the virtual inputs, i.e. DMU uses less virtual input will be better, rather than the virtual gaps reduction.
Although some weights may not be unique, the virtual inputs and outputs are. Since we focus on the virtual value, e.g. \( U_{j}^{*} y_{j} \), we therefore can ignore this uniqueness issue.
The advantages of the ECSW approach shown in this study are consistent with an earlier version (Ngo and Tripe, 2014), although that earlier study used data for 2013 only for New Zealand banks.
Readers are encouraged to look for more discussion regarding those variables, which are very popular in the banking (efficiency) literature, used in previous studies such as Altunbas et al. (2000), Chang et al. (2012), Kao and Liu (2013), and Ouenniche and Carrales (2018). There is no single agreed list of preferred variables, however, and other variables have been selected in other studies. As we discuss in Sect. 4.2 below, however, it is not obvious that a different set of variables would have any major impact on our results.
The Spearman’s ranking correlations between those measurements are all statistically significant at 1% level but were not reported to save space.
The t test for those differences or reductions are all statistically significant at 1% level but were not reported to save space.
Please note that banks with no credit rating scores are excluded and thus, the numbers of observations differ across the measurements (e.g. TR, SP or beta) and across the years.
One can also argue that DEA rankings are close to those of Standard & Poor’s as the relationship between SP and all DEA efficiency scores, no matter which weighting approach is used, is always found to be significantly positive (see rows 8–11 of Table 8).
References
Adler, N., Friedman, L., & Sinuany-Stern, Z. (2002). Review of ranking methods in the data envelopment analysis context. European Journal of Operational Research, 140(2), 249–265.
Altunbas, Y., Liu, M.-H., Molyneux, P., & Seth, R. (2000). Efficiency and risk in Japanese banking. Journal of Banking & Finance, 24(10), 1605–1628.
Andersen, P., & Petersen, N. C. (1993). A procedure for ranking efficient units in data envelopment analysis. Management Science, 39(10), 1261–1264.
Asmild, M., Hougaard, J. L., & Kronborg, D. (2013). Do efficiency scores depend on input mix? A statistical test and empirical illustration. Annals of Operations Research, 211(1), 37–48.
Barr, R. S., Durchholz, M. L., & Seiford, L. M. (1994). Peeling the DEA onion: Layering and rank-ordering DMUs using tiered DEA.
Bauer, P. W., Berger, A. N., Ferrier, G. D., & Humphrey, D. B. (1998). Consistency conditions for regulatory analysis of financial institutions: A comparison of frontier efficiency methods. Journal of Economics and Business, 50(2), 85–114.
Berger, A. N., & Humphrey, D. B. (1997). Efficiency of financial institutions: International survey and directions for future research. European Journal of Operational Research, 98(2), 175–212.
Botti, L. (2014). Corporate governance efficiency and internet financial reporting quality. Review of Accounting and Finance, 13(1), 43–64.
Boubaker, S., Manita, R., & Rouatbi, W. (2019). Large shareholders, control contestability and firm productive efficiency. Annals of Operations Research. https://doi.org/10.1007/s10479-019-03402-z.
Chang, T.-P., Hu, J.-L., Chou, R. Y., & Sun, L. (2012). The sources of bank productivity growth in China during 2002–2009: A disaggregation view. Journal of Banking & Finance, 36, 1997–2006.
Charnes, A., Cooper, W. W., & Rhodes, E. (1978). Measuring the efficiency of decision making units. European Journal of Operational Research, 2(6), 429–444.
Chok, N. S. (2010). Pearson’s versus Spearman’s and Kendall’s correlation coefficients for continuous data. Pittsburgh: University of Pittsburgh.
Coelli, T. J., Rao, D. S. P., O’Donnell, C. J., & Battese, G. E. (2005). An introduction to efficiency and productivity analysis (2nd ed.). Berlin: Springer.
Cooper, W. W., Seiford, L. M., & Tone, K. (2006). Data envelopment analysis: A comprehensive text with models, applications, references, and DEA-solver software (2nd ed.). Boston, MA: Springer.
Doyle, J. R. (1995). Multiattribute choice for the lazy decision maker: Let the alternatives decide! Organizational Behavior and Human Decision Processes, 62(1), 87–100.
Emrouznejad, A., Parker, B. R., & Tavares, G. (2008). Evaluation of research in efficiency and productivity: A survey and analysis of the first 30 years of scholarly literature in DEA. Socio-Economic Planning Sciences, 42(3), 151–157.
Feng, G., & Wang, C. (2018). Why European banks are less profitable than U.S. banks: A decomposition approach. Journal of Banking & Finance, 90, 1–16.
Fethi, M. D., & Pasiouras, F. (2010). Assessing bank efficiency and performance with operational research and artificial intelligence techniques: A survey. European Journal of Operational Research, 204, 189–198.
Fiordelisi, F., Marques-Ibanez, D., & Molyneux, P. (2011). Efficiency and risk in European banking. Journal of Banking & Finance, 35(5), 1315–1326.
Fujii, H., Managi, S., & Matousek, R. (2014). Indian bank efficiency and productivity changes with undesirable outputs: A disaggregated approach. Journal of Banking & Finance, 38, 41–50.
Hashimoto, A., & Wu, D. A. (2004). A DEA-compromise programming model for comprehensive ranking. Journal of the Operations Research Society of Japan, 47(2), 73–81.
Horn, R. A., & Johnson, C. R. (2012). Matrix analysis. Cambridge, MA: Cambridge University Press.
Jahanshahloo, G. R., Lotfi, F. H., Sanei, M., & Jelodar, M. F. (2008). Review of ranking models in data envelopment analysis. Applied Mathematical Sciences, 2(29), 1431–1448.
Jahanshahloo, G. R., Memariani, A., Lotfi, F. H., & Rezai, H. Z. (2005). A note on some of DEA models and finding efficiency and complete ranking using common set of weights. Applied Mathematics and Computation, 166, 265–281.
Kaffash, S., & Marra, M. (2017). Data envelopment analysis in financial services: A citations network analysis of banks, insurance companies and money market funds. Annals of Operations Research, 253(1), 307–344.
Kao, C., & Hung, H.-T. (2005). Data envelopment analysis with common weights: The compromise solution approach. Journal of Operational Research Society, 56, 1196–1203.
Kao, C., & Liu, S.-T. (2013). Multi-period efficiency measurement in data envelopment analysis: The case of Taiwanese commercial banks. Shillong: OMEGA.
Liu, F.-H. F., & Peng, H. H. (2008). Ranking units of the DEA frontier with common weights. Computers & Operations Research, 35, 1624–1637.
Liu, J. S., Lu, L. Y. Y., Lu, W.-M., & Lin, B. J. Y. (2013). A survey of DEA applications. OMEGA, 41(5), 893–902.
Liu, W., Sharp, J., & Wu, Z. (2006). Preference, production and performance in data envelopment analysis. Annals of Operations Research, 145(1), 105–127.
Ouenniche, J., & Carrales, S. (2018). Assessing efficiency profiles of UK commercial banks: A DEA analysis with regression-based feedback. Annals of Operations Research, 266(1), 551–587.
Ramezani-Tarkhorani, S., Khodabakhshi, M., Mehrabian, S., & Nuri-Bahmani, F. (2014). Ranking decision-making units using common weights in DEA. Applied Mathematical Modelling, 38(15–16), 3890–3896.
Ramón, N., Ruiz, J. L., & Sirvent, I. (2012). Common sets of weights as summaries of DEA profiles of weights: With an application to the ranking of professional tennis players. Expert Systems with Applications, 39(5), 4882–4889.
Roll, Y., & Golany, B. (1993). Alternate methods of treating factor weights in DEA. OMEGA, 21(1), 99–109.
Sealey, C. W., & Lindley, J. T. (1977). Inputs, outputs, and a theory of production and cost at depository financial institutions. Journal of Finance, 32(4), 1251–1266.
Seiford, L. M., & Thrall, R. M. (1990). Recent developments in DEA: The mathematical programming approach to frontier analysis. Journal of Econometrics, 46(1), 7–38.
Sensoy, A., Nguyen, D. K., Rostom, A., & Hacihasanoglu, E. (2019). Dynamic integration and network structure of the EMU sovereign bond markets. Annals of Operations Research, 281(1), 297–314.
Sexton, T. R., Silkman, R. H., & Hogan, A. J. (1986). Data envelopment analysis: Critique and extensions. New Directions for Program Evaluation, 32, 73–105.
Simar, L., & Wilson, P. W. (2007). Estimation and inference in two-stage, semi-parametric models of production processes. Journal of Econometrics, 136, 31–64.
Sturm, J.-E., & Williams, B. (2004). Foreign bank entry, deregulation and bank efficiency: Lessons from the Australian experience. Journal of Banking & Finance, 28(7), 1775–1799.
Thomson Reuters. (2019). Thomson Reuters Eikon. Retrieved from: https://eikon.thomsonreuters.com/index.html.
Tziogkidis, P., Matthews, K., & Philippas, D. (2018). The effects of sector reforms on the productivity of Greek banks: A step-by-step analysis of the pre-Euro era. Annals of Operations Research, 266(1), 531–549.
Wang, Y.-M., & Chin, K.-S. (2010). A neutral DEA model for cross-efficiency evaluation and its extension. Expert Systems with Applications, 37(5), 3666–3675.
Wang, Y.-M., Luo, Y., & Lan, Y.-X. (2011). Common weights for fully ranking decision making units by regression analysis. Expert Systems with Applications, 38(8), 9122–9128.
Zhu, W., Zhang, Q., & Wang, H. (2019). Fixed costs and shared resources allocation in two-stage network DEA. Annals of Operations Research, 278(1), 177–194.
Zohrehbandian, M., Makui, A., & Alinezhad, A. (2010). A compromise solution approach for finding common weights in DEA: An improvement to Kao and Hung’s approach. Journal of the Operational Research Society, 61, 604–610.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Hammami, H., Ngo, T., Tripe, D. et al. Ranking with a Euclidean common set of weights in data envelopment analysis: with application to the Eurozone banking sector. Ann Oper Res 311, 675–694 (2022). https://doi.org/10.1007/s10479-020-03759-6
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10479-020-03759-6