Président du jury Decaestecker, Christine
Promoteur Vincke, Philippe
Publication Non publié, 2007-10-31
| Résumé : | Multi-criteria decision aid has emerged from the operational research field as the answer given to a couple of important questions encountered in complex decisions problems. Firstly, as decision aiding tools, such methods do not replace the decision maker with a mathematical model, but support him to construct his solution by describing and evaluating his options. Secondly, instead of using a unique criterion capturing all aspects of the problem, in the multi-criteria decision aid methods one seeks to build multiple criteria, representing several points of view. This work explores the application of multi-criteria decision aid methods for optimising food chain countermeasure strategies after a radioactive release to the environment. The core of the thesis is dedicated to formulating general lines for the development of a multi-criteria decision aid model. This includes the definition of potential actions, construction of evaluation criteria and preference modelling and is essentially based on the results of a stakeholders’ process. The work is centred on the management of contaminated milk in order to provide a concrete focus and because of its importance as an ingestion pathway in short term after an accident. Among other issues, the public acceptance of milk countermeasures as a key evaluation criterion is analysed in detail. A comparison of acceptance based on stochastic dominance is proposed and, based on that, a countermeasures’ acceptance ranking is deduced. In order to assess “global preferences” taking into account all the evaluation criteria, an ordinal method is chosen. This method allows expressing the relative importance of criteria in a qualitative way instead of using, for instance, numerical weights. Some algorithms that can be used for robustness analysis are also proposed. This type of analysis is an alternative to sensitivity analysis in what concerns data uncertainty and imprecision and seeks to determine how and if a model result or conclusion obtained for a specific instance of a model’s parameters holds over the entire domain of acceptable values for these parameters. The integrated multi-criteria decision aid approach proposed makes use of outranking and interactive methodologies and is implemented and tested through a number of case studies and prototype tools. |
