Browsing by Author "Despotis, Dimitris K."
Now showing 1 - 5 of 5
Results Per Page
Sort Options
- Assessment of OECD Better Life Index by incorporating public opinionPublication . Koronakos, Gregory; Smirlis, Yiannis; Sotiros, Dimitris; Despotis, Dimitris K.Well-being has a multidimensional nature as it depends on multifaceted factors such as material conditions and quality of life. The Organization for Economic Co-operation and Development (OECD) has developed the Better Life Index (BLI) as part of the OECD Better Life initiative to facilitate the better understanding of what drives well-being of people. The BLI is a three-level hierarchical composite indicator that covers several socio-economic aspects. In this paper, considering the entire hierarchical structure of the index, we introduce a bottom-up procedure for the aggregation of the components at each level. We formulate the assessment of BLI as a multiple objective programming (MOP) problem that facilitates the implementation of different concepts to derive different aggregation schemes. We incorporate the data from previous years into the normalization process of the indicators, to take into account the discrepancy on their observed values and smooth their deviations across the years. Also, we consider the public opinion about well-being that is captured from the worldwide responses in the web platform of OECD BLI. We incorporate the public opinion into the assessment models in the form of weight restrictions. In this way, we reduce the effect of compensation that might be imposed by the adopted modelling approach. We apply our methodology to the data of 38 countries (35 OECD and 3 non-OECD economies) for the year 2017. Our findings illustrate that the public opinion in the form of weight restrictions can effectively drive the optimization process and depict the collective preferences to the BLI scores.
- Dominance at the divisional efficiencies level in network DEA: the case of two-stage processesPublication . Sotiros, Dimitris; Koronakos, Gregory; Despotis, Dimitris K.We introduce in this paper the notion of dominance in the divisional efficiencies space in Network Data Envelopment Analysis. We argue that, irrespectively of the method used, a successful efficiency evalua- tion protocol should satisfy the dominance property at the divisional efficiencies level. In particular, there should not exist any other feasible solution in the assessment model, suboptimal in terms of the opti- mality criterion, that provides stage efficiencies scores at least as high as the assessed ones and higher for at least one stage. Then, we investigate the dominance property in different methods for two-stage series processes of various complexity. We prove that the additive efficiency decomposition method and the relational model provide non-dominated divisional efficiencies when they are applied to elemen- tary two-stage processes, where nothing but the external inputs to the first stage enters the system and nothing but the external outputs of the second stage leaves the system. For more complex two-stage structures, however, we provide examples showing that these models do not comply with the dominance requirement at the divisional efficiencies level and lead to controversial results. Finally, we revisit some characteristic NDEA methods for which dominance is an inherent property.
- Dominance at the divisional efficiencies level in network DEA: the case of two-stage processesPublication . Sotiros, Dimitris; Koronakos, Gregory; Despotis, Dimitris K.We introduce in this paper the notion of dominance in the divisional efficiencies space in Network Data Envelopment Analysis. We argue that, irrespectively of the method used, a successful efficiency evaluation protocol should satisfy the dominance property at the divisional efficiencies level. In particular, there should not exist any other feasible solution in the assessment model, suboptimal in terms of the optimality criterion, that provides stage efficiencies scores at least as high as the assessed ones and higher for at least one stage. Then, we investigate the dominance property for the relational model and the additive efficiency decomposition method for general two-stage series processes. We provide an example showing that these methods do not comply with the dominance requirement at the divisional efficiencies level and lead to controversial results.
- Reformulation of Network Data Envelopment Analysis models using a common modelling frameworkPublication . Koronakos, Gregory; Sotiros, Dimitris; Despotis, Dimitris K.Network Data Envelopment Analysis (network DEA) is an extension of the conventional Data Envelop- ment Analysis (DEA) developed to take into account the internal structure of the Decision Making Units (DMUs). In network DEA, the DMU is considered as a network of interconnected sub-processes, where the connections indicate the flow of the intermediate measures. In this paper, we reformulate some of the basic network DEA methodologies in a common modelling framework. We show that the leader- follower approach, the multiplicative and the additive decomposition methods as well as the recently introduced min-max method and the “weak-link”approach, can all be modelled in a multi-objective programming framework, differentiating only in the definition of the overall system efficiency and the solution procedure adopted. Such a common modelling framework makes the direct comparison of the different methodologies possible and enables us to spot and underline their similarities and dissimilar- ities effectively. We illustrate graphically how the aforementioned methodologies locate their optimal efficiency scores on the Pareto front in the objective functions space, with an example taken from the literature.
- Review and improvements on OECD better life indexPublication . Koronakos, Gregory; Smirlis, Yiannis; Sotiros, Dimitris; Despotis, Dimitris K.The Organization for Economic Cooperation and Development (OECD) has developed the Better Life Index (BLI) as part of the OECD Better Life initiative to facilitate the better understanding of what drives well-being of people and guide the policy-making. The BLI is a three-level hierarchical composite indicator which covers several socio-economic aspects. In this paper, we depart from the traditional approaches of building composite indices by introducing a hierarchical evaluation methodology for the assessment of BLI. We establish a common basis for fair and democratic evaluation as the aggregation schemes for both first and second level of BLI are determined jointly by the assessed countries through optimization process. We also incorporate into the assessment the public opinion that is captured from the worldwide responses in the web platform of OECD BLI. In addition, we enrich our methodology by incorporating the data from previous years into the normalization process of the indicators, thus smoothing the deviations of indicators’ values among the years. We apply our approach to the data of 38 countries for the year 2017. The robust results obtained from our approach provide insights about the key role that public opinion plays in the evaluation of BLI.