Article Contents
Article Contents

# A new method for ranking decision making units using common set of weights: A developed criterion

• * Corresponding author: Gholam Hassan Shirdel
• In this paper we have developed a new model by altering Liu and Peng's approach [20] toward ranking method using CSW. In fact, we have adopted a new criterion which is stronger in terms of maximizing efficiencies. After showing advantages of our model theoretically and illustrating it geometrically, two examples demonstrated how the proposed method is practically more capable.

Mathematics Subject Classification: Primary: 90C05, 90C29; Secondary: 90B50.

 Citation:

• Figure 1.  $0<y_P<x_P, \Delta_P = x_p-y_p ,m_p = {y_p \over x_p} , o<m_{p_1}<m_P<m_{p_2}$

Figure 2.  The interior points of the area $OQ_1P$, $R_1$, have less amount of $\Delta$ than $P$ while slopes of crossing lines from the origin and these points are less than $m_P$

Figure 3.  Slopes of crossing lines from the origin and the points located in the areas $R_1$ and $R_2$ are less than $m_P$

Figure 4.  Range of slopes of the lines crossing the origin and the points located in $R_3$ is the same as that for the the points located in the area enclosed by the segments $OP$, $OQ_6$ and $Q_6P$.

Figure 5.  Slope of the line crossing the origin and $P^{(U_1,V_1)}_o$ is maximum.

Figure 6.  Two pairs of DMUs with the same efficiency scores.

Table 1.  Input and Output data of DMUs

 $DMU_j$ $x_{1j}$ $x_{2j}$ $x_{3j}$ $x_{4j}$ $y_{1j}$ $y_{2j}$ $DMU_1$ 995 6205 1375 2629 4127 1678 $DMU_2$ 917 5898 1379 2047 3721 1277 $DMU_3$ 3178 10049 3615 3511 2706 2051 $DMU_4$ 813 5833 1124 1730 2176 1538 $DMU_5$ 1236 8639 2486 4990 5220 2042 $DMU_6$ 1146 7610 1600 3589 3517 1856 $DMU_7$ 705 5600 1557 3623 2352 2060 $DMU_8$ 2871 11524 2880 2452 1755 1664 $DMU_9$ 1098 8998 1730 2823 4412 2334 $DMU_{10}$ 2032 9383 2421 4454 5386 2080 $DMU_{11}$ 1414 10468 2140 3649 5735 2691 $DMU_{12}$ 1967 11260 2759 3178 6079 2804 $DMU_{13}$ 1851 9880 2335 4570 5893 2495 $DMU_{14}$ 3100 15649 5487 2940 5248 3692 $DMU_{15}$ 5016 18010 4008 3567 7800 4852 $DMU_{16}$ 1924 12682 2490 2975 6040 3396

Table 2.  The generated common set of weights

 $v^*_1$ $v^*_2$ $v^*_3$ $v^*_4$ $u^*_1$ $u^*_2$ Our method 0.000001 0.181081 0.000001 0.124392 0.116466 0.578059 Liu and Peng's method [20] 0.000001 0.000001 0.000001 7.50E-07 8.70E- 07 0.000004

Table 3.  The efficiencies

 $DMU_j$ $E^*_j$ CWA-Efficiency CCR-Efficiency $DMU_1$ 1 1 1 $DMU_2$ 0.885761 0.877007 1 $DMU_3$ 0.665101 0.55716 0.690363 $DMU_4$ 0.89857 0.911488 1 $DMU_5$ 0.818436 0.807723 1 $DMU_6$ 0.812557 0.823997 0.881091 $DMU_7$ 1 1 1 $DMU_8$ 0.48762 0.440469 0.555791 $DMU_9$ 0.940676 0.968986 1 $DMU_{10}$ 0.812047 0.774854 0.863042 $DMU_{11}$ 0.94638 0.963253 0.996068 $DMU_{12}$ 0.956693 0.920591 1 $DMU_{13}$ 0.90288 0.884299 0.915511 $DMU_{14}$ 0.858084 0.75116 1 $DMU_{15}$ 0.960084 0.867478 1 $DMU_{16}$ 1 1 1

Table 4.  The average of the efficiencies in each method and their ratio

 Our method Liu and Peng's method [20] The ratio 0.871556 0.846779 1.02926

Table 5.  The ranking scores

 $DMU_j$ Our method: Input-oriented approach Our method: Output-oriented approach CWA-ranking CCR $DMU_1$ 1 3 2 1 $DMU_2$ 10 10 9 1 $DMU_3$ 15 15 15 6 $DMU_4$ 9 9 7 1 $DMU_5$ 12 12 12 1 $DMU_6$ 13 13 11 4 $DMU_7$ 2 2 3 1 $DMU_8$ 16 16 16 7 $DMU_9$ 7 7 4 1 $DMU_{10}$ 14 14 13 5 $DMU_{11}$ 6 6 5 2 $DMU_{12}$ 5 5 6 1 $DMU_{13}$ 8 8 8 3 $DMU_{14}$ 11 11 14 1 $DMU_{15}$ 4 4 10 1 $DMU_{16}$ 3 1 1 1

Table 6.  The averages of the obtained efficiencies and their ratio in each case

 Size of the sample Our method CWA-Efficiencies The ratio 6 0.916128 0.906961 1.010107 12 0.539086 0.539082 1.000006 25 0.689937 0.148176 4.656189 50 0.550724 0.553320 0.995309 100 0.639243 0.471678 1.355254 200 0.582310 0.580711 1.002753
•  [1] N. Adler, L. Friedman and Z. Sinuany-Stern, Review of ranking methods in the data envelopment analysis context, Eur J Oper Res, 140 (2002), 249-265.  doi: 10.1016/S0377-2217(02)00068-1. [2] N. Aghayi, M. Tavana and M. A. Raayatpanah, Robust efficiency measurement with common set of weights under varying degrees of conservatism and data uncertainty, Eur J. Ind Eng, 10 (2016), 385-405.  doi: 10.1504/EJIE.2016.076386. [3] A. Aldamak and S. Zolfaghari, Review of efficiency ranking methods in data envelopment analysis, Meas, 106 (2017), 161-172.  doi: 10.1016/j.measurement.2017.04.028. [4] R. D. Banker, A. Charnes and W. W. Cooper, Some models for estimating technical and scale inefficiencies in data envelopment analysis, Manage Sci, 30 (1984), 1031-1142.  doi: 10.1287/mnsc.30.9.1078. [5] A. Charnes, W. W. Cooper and E. Rhodes, Measuring the efficiency of DMUs, Eur J Oper Res, 2 (1978), 429-444.  doi: 10.1016/0377-2217(78)90138-8. [6] C. I. Chiang, M. J. Hwang and Y. H. Liu, Determining a common set of weights in a DEA problem using a separation vector, Math and Comput Model, 54 (2002), 2464-2470.  doi: 10.1016/j.mcm.2011.06.002. [7] C. I. Chiang and G. H. Tzeng, A new efficiency measure for DEA: Efficiency achievement measure established on fuzzy multiple objectives programming, J Manage, 17 (2000), 369-388. [8] W. D. Cook, Y. Roll and A. Kazakov, A DEA model for measuring the relative efficiency of highway maintenance patrols, Inform Syst Oper Res, 28 (1990), 113-124. [9] D. K. Despotis, Improving the discriminating power of DEA: Focus on globally efficient units, J Oper Res Soc, 53 (2002), 314-323.  doi: 10.1057/palgrave.jors.2601253. [10] J. A. Ganley and S. A. Cubbin, Public Sector Efficiency Measurement: Applications of Data Envelopment Analysis, North-Holland, Amsterdam, 1992. [11] A. Hatami Marbini, M. Tavana, P. J. Agrell, F. Hosseinzadeh Lotfi and Z. Ghelej Beigi, A common-weights DEA model for centralized resource reduction and target setting, Comput Ind Eng, 79 (2015), 195-203. [12] F. Hosseinzadeh Lotfi, M. Rostamy-Malkhlifeh, G. R. Jahanshahloo, Z. Moghaddas, M. Khodabakhshi and M. Vaez-Ghasemi, A review of ranking models in data envelopment analysis, J Appl Math., 2013 (2013), Article ID: 492421, 20 pages. [13] C. K. Hu, F. B. Liu and C. F. Hu, Efficiency measures in fuzzy data envelopment analysis with common weights, J Ind Manage Opt, 13 (2017), 237-249.  doi: 10.3934/jimo.2016014. [14] C. L. Hwang and A. S. M. Masud, Multiple Objective Decision Making: Methods and Applications, Springer, Berlin, 1979. [15] G. R. Jahanshahloo, F. Hosseinzadeh Lotfi, M. Khanmohammadi, M. Kazemimanesh and V. Rezaie, Ranking of units by positive ideal DMU with common weights, Expert Syst Appl, 37 (2010), 7483-7488.  doi: 10.1016/j.eswa.2010.04.011. [16] C. Kao and H. Hung, Data envelopment analysis with common weights: The comprise solution approach, J Oper Res Soc, 56 (2005), 1196-1203.  doi: 10.1057/palgrave.jors.2601924. [17] M. N. Kritikos, A full ranking methodology in data envelopment analysis based on a set of dummy decision making units, Expert Systems with Applications: An International Journal, 77 (2017), 211-225.  doi: 10.1016/j.eswa.2017.01.042. [18] F. Li, J. Song, A. Dolgui and L. Liang, Using common weights and efficiency invariance principles for resource allocation and target setting, International J Prod Res, 55 (2017), 4982-4997.  doi: 10.1080/00207543.2017.1287450. [19] R. Lin, Z. Chen and Z. Li, A new approach for allocating fixed costs among decision making units, J Ind Manag Optim, 12 (2016), 211-228.  doi: 10.3934/jimo.2016.12.211. [20] F. H. F. Liu and H. H. Peng, Ranking of units on the DEA frontier with common weights, Comput Oper Res, 35 (2008), 1624-1637.  doi: 10.1016/j.cor.2006.09.006. [21] S. Mehrabian, G. R. Jahanshahloo, M. R. Alirezaei and G. R. Amin, An assurance interval of the non-archimedean epsilon in DEA models, Eur J Oper Res, 48 (2000), 189-350.  doi: 10.1287/opre.48.2.344.12381. [22] J. X. Nan and D. F. Li, Linear programming technique for solving interval-valued constraint matrix games, J Ind Manag Optim Optimization, 10 (2014), 1059-1070.  doi: 10.3934/jimo.2014.10.1059. [23] J. Pourmahmoud and Z. Zeynali, A nonlinear model for common weights set identification in network Data Envelopment Analysis, Int J Ind Math, 38 (2016), 87-98. [24] A. Rahman, S. Lee and T. C. Chung, Accurate multi-criteria decision making methodology for recommending machine learning algorithm, J Expert Syst Appl: An International Journal archive, 71 (2017), 257-278. [25] S. Ramazani-Tarkhorani, M. Khodabakhshi, S. Mehrabian and F. Nuri-Bahmani, Ranking decision-making units using common weights in DEA, Appl Math Model, 38 (2014), 3890-3896.  doi: 10.1016/j.apm.2013.08.029. [26] Y. Roll, W. D. Cook and B. Golany, Controlling factor weighs in data envelopment analysis, IIE Trans, 23 (1991), 2-9. [27] S. Saati, A. Hatami-Marbini, P. J. Agrell and M. Tavana, A common set of weight approach using an ideal decision making unit in data envelopment analysis, Journal of Industrial and Management Optimization, 8 (2012), 623-637.  doi: 10.3934/jimo.2012.8.623. [28] M. Salahi, N. Torabi and A. Amiri, An optimistic robust optimization approach to common set of weights in DEA, Meas, 93 (2016), 67-73.  doi: 10.1016/j.measurement.2016.06.049. [29] G. H. Shirdel, S. Ramezani-Tarkhorani and Z. Jafari, tA Method for Evaluating the Performance of Decision Making Units with Imprecise Data Using Common Set of Weights, Int J Appl Comput Math, 3 (2017), 411-423.  doi: 10.1007/s40819-016-0152-0. [30] J. Sun, J. Wu and D. Guo, Performance ranking of units considering ideal and anti-ideal DMU with common weights, Appl Math Model, 37 (2013), 6301-6310.  doi: 10.1016/j.apm.2013.01.010. [31] K. Tone, On returns to scale under weight restrictions in data envelopment analysis, J Prod Anal, 16 (2001), 31-47. [32] Y. M. Wang, Y. Luo and Y. X. Lan, Common weights for fully ranking decision making units by regression analysis, Expert Syst Appl, 38 (2011), 9122-9128.  doi: 10.1016/j.eswa.2011.01.004.

Figures(6)

Tables(6)