Non-parametric approaches for the performance measurement of units with complex internal structure
Grant no.: NCN 2020/37/B/HS4/03125
Funding agency: National Science Centre (NCN), Poland
Funding scheme: OPUS
Funding period: 1.02.2021-31.01.2024 (36 months)
Budget: 496 800 PLN
Title in Polish: Nieparametryczne podejścia do pomiaru wydajności jednostek o złożonej strukturze wewnętrznej
Principal Investigator (Kierownik):
Senior Investigators (Główni wykonawcy):
- Gregory Koronakos (U.Pireus, GR)
- Barbara Kamińska
- Julia Nasiadka
– Ph.D. / M.Sc. / B.Sc. student
Aims and scope:
Network DEA (NDEA) is a major extension of conventional Data Envelopment Analysis (DEA) that takes into consideration the internal structure of the DMUs. In particular, NDEA conceives the production process of the Decision Making Units (DMUs) as a network of interconnected sub-processes that are linked with intermediate measures. Although the existing NDEA models have dealt with several drawbacks that standard DEA models face when they are applied on DMUs with a complex internal structure, there are still open research questions in this field. The peculiarities observed under the variable returns-to-scale assumption, the “non-equivalence” between the multiplier (primal) and the envelopment (dual) forms as well as the inadequacy of deriving projections that render efficient the DMUs are some of the major issues that characterize NDEA models, which can lead to ineffective managerial decisions. The aim of this project is to shed light on these issues and to develop new methods and models that amend them by carrying out the following four tasks:
- Development of a new approach to obtain “characteristic” divisional efficiency scores in multi-stage series structures when the efficiency decomposition is not unique under the multiplicative approach.
- Development of a method to derive unbiased divisional efficiency scores for DMUs with a parallel internal structure.
- Development of new models that can be straightforwardly applied under the VRS assumption and satisfy the fundamental DEA properties.
- Develop new models capable of projecting inefficient DMUs onto the efficiency frontier.
The results of this project are expected to strengthen the theoretical foundations of NDEA and to provide practitioners and experts with enhanced NDEA models, which would allow to cover a wider set of real-world entities’ types with a reliable performance measurement method.
Peer-reviewed articles in JCR-listed journals
- G. Koronakos, D. Sotiros, D.K. Despotis, M.N. Kritikos (2022) Fair efficiency decomposition in network DEA: A compromise programming approach, Socio-Economic Planning Sciences 79, 101100.
- D. Sotiros, V. Rodrigues, M.C. Silva (2022) Analysing the export potentials of the Portuguese footwear industry by data envelopment analysis, Omega 108, 102560.
Peer-reviewed articles in non JCR-listed journals
Forthcoming publications, submitted papers and work in progress
- G. Koronakos, Y. Smirlis, D. Sotiros, D.K. Despotis (2021) The OECD Better Life Index: A guide for well-being based economic diplomacy, Palgrave Macmillan’s International Political Economy Series, submitted.