Abstract
One of the major challenges in measuring efficiency in terms of resources and outcomes is the assessment of the evolution of units over time. Although Data Envelopment Analysis (DEA) has been applied for time series datasets, DEA models, by construction, form the reference set for inefficient units (lambda values) based on their distance from the efficient frontier, that is, in a spatial manner. However, when dealing with temporal datasets, the proximity in time between units should also be taken into account, since it reflects the structural resemblance among time periods of a unit that evolves. In this paper, we propose a twostage spatiotemporal DEA (ST DEA) approach, which captures both the spatial and temporal dimension through a multiobjective programming model. In the first stage, DEA is solved iteratively extracting for each unit only previous DMUs as peers in its reference set. In the second stage, the lambda values derived from the first stage are fed to a Multiobjective Mixed Integer Linear Programming model, which filters peers in the reference set based on weights assigned to the spatial and temporal dimension. The approach is demonstrated on a realworld example drawn from software development.
This is a preview of subscription content, access via your institution.
References
Andersen, P., & Petersen, N. C. (1993). A procedure for ranking efficient units in data envelopment analysis. Management Science, 39(10), 1261–1264.
Anderson, T. R., & Inman, L. (2011). Resolving the issue of multiple optima in Technology Forecasting using Data Envelopment Analysis. In IEEE Proceedings of PICMET’11 Technology Management in the Energy Smart World (PICMET) 2011, (pp. 1–5).
Avkiran, N. K. (2009a). Opening the black box of efficiency analysis: An illustration with UAE banks. Omega, 37(4), 930–941.
Avkiran, N. K. (2009b). Removing the impact of environment with unitsinvariant efficient frontier analysis: An illustrative case study with intertemporal panel data. Omega, 37(3), 535–544.
Avkiran, N. K., & Rowlands, T. (2008). How to better identify the true managerial performance: State of the art using DEA. Omega, 36(2), 317–324.
Banker, R. D., Cooper, W. W., Seiford, L. M., & Zhu, J. (2011). Returns to scale in DEA. In W. W. Cooper, L. M. Seiford, & J. Zhu (Eds.), Handbook on Data Envelopment Analysis (pp. 41–70). New York: Springer.
Bergendahl, G. (1998). DEA and benchmarks—An application to Nordic banks. Annals of Operations Research, 82, 233–250.
Brooke, A., Kendrick, D., Meeraus, A., & Raman, R. (2003). GAMS/CPLEX 9.0. user notes. Washington, DC: GAMS Development Corp.
Cao, Y., & Yang, Z. (2009). Using DEA window analysis and the Malmquist index to evaluate the operations of Canadian Schedule I banks. In IEEE/INFORMS International Conference on Service Operations, Logistics and Informatics, 2009. SOLI’09, (pp. 353–358).
Charnes, A., Clark, C. T., Cooper, W. W., & Golany, B. (1984). A developmental study of data envelopment analysis in measuring the efficiency of maintenance units in the US air forces. Annals of Operations Research, 2(1), 95–112.
Charnes, A., Cooper, W. W., & Rhodes, E. (1978). Measuring the efficiency of decision making units. European Journal of Operational Research, 2(6), 429–444.
Charnes, A., Cooper, W. W., & Rhodes, E. (1981). Evaluating program and managerial efficiency: An application of data envelopment analysis to program follow through. Management Science, 27(6), 668–697.
Chen, W.C., & Johnson, A. L. (2010). The dynamics of performance space of Major League Baseball pitchers 1871–2006. Annals of Operations Research, 181(1), 287–302.
Chen, P.C., & Yu, M.M. (2014). Total factor productivity growth and directions of technical change bias: Evidence from 99 OECD and nonOECD countries. Annals of Operations Research, 214(1), 143–165.
Coelli, T. J., Prasada Rao, D. S., O’Donnell, C. J., & Battese, G. E. (2005). An introduction to efficiency and productivity analysis. New York: Springer.
Cook, W. D., & Seiford, L. M. (2009). Data envelopment analysis (DEA)Thirty years on. European Journal of Operational Research, 192(1), 1–17.
Cooper, W. W., Seiford, L. M., & Tone, K. (2007). Data envelopment analysis: A comprehensive text with models, applications, references and DEAsolver software. New York: Springer.
Couto, C., Maffort, C., Garcia, R., & Valente, M. T. (2013). COMETS: A dataset for empirical research on software evolution using source code metrics and time series analysis. ACM SIGSOFT Software Engineering Notes, 38(1), 1–3.
Emrouznejad, A. (2003). An alternative DEA measure: A case of OECD countries. Applied Economics Letters, 10(12), 779–782.
Emrouznejad, A., & Thanassoulis, E. (2005). A mathematical model for dynamic efficiency using data envelopment analysis. Applied Mathematics and Computation, 160(2), 363–378.
Emrouznejad, A., & Thanassoulis, E. (2010). Measurement of productivity index with dynamic DEA. International Journal of Operational Research, 8(2), 247–260.
Färe, R., Grosskopf, S., & Lovell, C. K. (1994). Production frontiers. Cambridge, UK: Cambridge University Press.
Freed, N., & Glover, F. (1981). Simple but powerful goal programming models for discriminant problems. European Journal of Operational Research, 7(1), 44–60.
GrifellTatjé, E., & Lovell, C. K. (1997). A DEAbased analysis of productivity change and intertemporal managerial performance. Annals of Operations Research, 73, 177–189.
Hashimoto, A., & Kodama, M. (1997). Has livability of Japan gotten better for 1956–1990?: A DEA approach. Social Indicators Research, 40(3), 359–373.
Inuiguchi, M., & Mizoshita, F. (2012). Qualitative and quantitative data envelopment analysis with interval data. Annals of Operations Research, 195(1), 189–220.
Jain, S., Triantis, K. P., & Liu, S. (2011). Manufacturing performance measurement and target setting: A data envelopment analysis approach. European Journal of Operational Research, 214(3), 616–626.
Lozano, S., & Villa, G. (2010). Gradual technical and scale efficiency improvement in DEA. Annals of Operations Research, 173(1), 123–136.
Lynde, C., & Richmond, J. (1999). Productivity and efficiency in the UK: A time series application of DEA. Economic Modelling, 16(1), 105–122.
Moreno, P., Lozano, S., & Gutiérrez, E. (2013). Dynamic performance analysis of US wireline telecommunication companies. Telecommunications Policy, 37(6–7), 469–482.
Movahedi, M. M., Saati, S., & Vahidi, A. R. (2007). Iranian railway efficiency (1971–2004): An application of DEA. International Journal of Contemporary Mathematical Sciences, 2, 1569–1579.
Parnas, D. L. (1994). Software aging. In Proceedings of the 16th international conference on Software engineering, (pp. 279–287). Los Alamitos, CA, USA: IEEE Computer Society Press.
Rosenthal, R. E. (2013). A GAMS tutorial. In GAMS Development Corporation (Eds.), GAMS: A user’s guide (pp. 7–28). Washington, DC, USA.
Rutledge, R. W., Parsons, S., & Knaebel, R. (1995). Assessing hospital efficiency over time: An empirical application of data envelopment analysis. Journal of Information Technology Management, 6, 13–24.
Samoladas, I., Gousios, G., Spinellis, D., & Stamelos, I. (2008). The SQOOSS quality model: Measurement based open source software evaluation. In B. Russo, E. Damiani, S. Hissam, B. Lundell, & G. Succi (Eds.), Open source development, communities and quality (pp. 237–248). New York: Springer.
Seiford, L. M., & Zhu, J. (1998). On alternative optimal solutions in the estimation of returns to scale in DEA. European Journal of Operational Research, 108(1), 149–152.
Acknowledgments
Konstantinos Petridis would like to acknowledge that part of this work was cofunded within the framework of the Action “State Scholarships Foundation’s (IKY) mobility grants programme for the short term training in recognized scientific/research centers abroad for candidate doctoral or postdoctoral researchers in Greek universities or research” from the European Social Fund (ESF) programme “Lifelong Learning Programme 2007–2013”.
Author information
Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Appendices
Appendix 1: Proof of Proposition 1
Let us assume that a DMU(3) is inefficient and \(\lambda _1\), \(\lambda _2\) are two nonzero lambdas of its reference set corresponding to DMU(1) and DMU(2) respectively, and assume that \(\lambda _1 >\lambda _2 \), such that:
According to the temporal dimension, DMU(3) is closer to DMU(2), while according to the spatial dimension DMU(3) has a higher resemblance to DMU(1).
The corresponding efficiency from (3) will be \(\varphi \le \frac{1}{y_3}\cdot \left( {\lambda _1\cdot y_1+\lambda _2\cdot y_2}\right) \) (where \(y_3\) is the output of the DMU under study) and due to (24), the above inequality will be reformulated as follows:
The efficiency provided by the ST DEA model will be the following:
Therefore, the efficiency \({\hat{\varphi }}\) is calculated from (9) by selecting the combination of \(y_1\), \(y_2\) that maximizes the value of \({\hat{\varphi }}\) satisfying the constraint. In the right hand side of inequalities (27) and (28), lambda values are omitted due to the constraints (9) and (11) of the ST DEA model.
In order to prove that \(\varphi \ge {\hat{\varphi }}\forall y\) the relative position of \(\varphi \) and \({\hat{\varphi }}\) by means of order relationships should be investigated. For this reason, two scenarios about the arrangement of \(y_1\) and \(y_2\) are examined:

\(y_1<y_2\)
In this case, \(y_2+\left( {y_1y_2}\right) \cdot \lambda _1<y_2\) as \(\left( {y_1y_2}\right) \cdot \lambda _1<0\) (for the sake of simplicity denominator \(y_3\) is dropped from the analysis since it is equal to all instances). To investigate the order relation of \(y_2+\left( {y_1y_2}\right) \cdot \lambda _1\) with \(y_1\), we reformulate the right hand side of inequality (26) with respect to \(y_1\) as follows:
From (29), it can be seen that as \(\left( {y_2y_1}\right) \cdot \lambda _2>0\), then \(y_1+\left( {y_2y_1}\right) \cdot \lambda _2>y_1\). Therefore, the following order relationship is formulated:
The initial assumption \(y_1<y_2\) is reformulated as \(y_2=y_1+k\), where k is a real nonnegative number. By substitution in (26), the following is derived:
Comparing the right hand sides of inequalities (27) and (31), it is obvious that \(y_1+\lambda _2\cdot k>y_1\), consequently, \(\varphi \ge {\hat{\varphi }}\).

\(y_1 >y_2 \)
In this case \(y_1 +\left( {y_2 y_1 } \right) \cdot \lambda _2 <y_1 \) as \(\left( {y_2 y_1 } \right) \cdot \lambda _2 <0\). To investigate the order relationship with \(y_2 \), we reformulate (22) with respect to \(y_2 \) as follows:
From (30), it can be seen that as \(\left( {y_2 y_1 } \right) \cdot \lambda _2 >0\), then \(y_2 +\left( {y_1 y_2 } \right) \cdot \lambda _1>y_2\). Therefore, the following order relationship is formulated:
The initial assumption \(y_1 <y_2 \) is reformulated as \(y_1 =y_2 +m\), where m is a real nonnegative number. By substitution in (26), the following is derived:
Comparing the right hand sides of inequalities (28) and (34), it is obvious that \(y_2 +\lambda _1\cdot m>y_2\), consequently, \(\varphi \ge {\hat{\varphi }}\).
Appendix 2: Proof of Proposition 2
Let \(\lambda _i^{DEA}\in {\mathcal {F}}^{DEA}\) be the optimal lambdas of DEA output model described by (1)–(4), \(\lambda _i^{ST\,DEA}\in {\mathcal {F}}^{ST\,DEA}\) be the optimal lambdas of ST DEA model, described by (9)–(13), and \({\mathcal {F}}^{\bullet }\) be the efficiency set of model \(\bullet \). By construction of tables A and \({\varvec{\Delta }}\), a lambda that appears in \({\mathcal {F}}^{DEA}\) will also appear in \({\mathcal {F}}^{ST\,DEA}\). From the ST DEA model, only one weight dependent solution will be selected among the lambdas provided by the initial DEA model (1)–(4) and thus, the feasibility of the model is guaranteed and furthermore it stands that: \({\mathcal {F}}^{ST\,DEA}\subseteq {\mathcal {F}}^{DEA}\).
Rights and permissions
About this article
Cite this article
Petridis, K., Chatzigeorgiou, A. & Stiakakis, E. A spatiotemporal Data Envelopment Analysis (ST DEA) approach: the need to assess evolving units. Ann Oper Res 238, 475–496 (2016). https://doi.org/10.1007/s1047901520458
Published:
Issue Date:
Keywords
 Data Envelopment Analysis
 Efficiency
 OR in software
 Multiobjective programming
 Linear Programming