Euro is the "Association of European Operational Research Societies"
within IFORS, the "International Federation of Operational Research Societies"

• Home
• Prizes and Awards
• Doctoral Dissertation Award (EDDA)

Keywords: Decision aiding, Robustness analysis, Robust ordinal regression, Preference modeling, Preference disaggregation, Outranking relation, Additive value function

We propose a set of novel decision aiding methods based on two prevailing preference models: additive value function and outranking relation. The introduced approaches take into account preference information of a new type and conduct robustness analysis of the suggested recommendation in an innovative way. The proposed robust ordinal regression procedures account for indirect, imprecise, and incomplete preference information provided by the decision makers (DMs). This includes the traditionally used pairwise comparisons or assignment examples, which are, however, decomposed in an original way to parameters of the generalized outranking- or value-based models. Additionally, we consider other types of preference information which so far has not received due attention in Multiple Criteria Decision Aiding. These are rank-related requirements in the form of desired positions and scores, possibly imprecise desired class cardinalities, or real intervals for indifference and preference thresholds. When it comes to robustness analysis, we present new methods for exploiting the consequences of applying all preference models compatible with the provided preferences. In particular, we implement reasoning in terms of the necessary and possible consequences for outranking methods and group decision problems. We also propose the framework of extreme ranking analysis and procedures for selection of a representative preference model instance. In this way, the introduced approaches identify the recommendation observed in case of all, some, the most favorable, the least advantageous, or the most robust compatible model for the considered preferences. When confronted with the value system of the DM, these results can be used for looking more thoroughly into the subject, by exploring, reasoning, or testing scenarios. Thus, the presented methods promote alternate phases of preference elicitation and robustness analysis as a versatile tool for approaching real-world decision problems.

During the upcoming decades, healthcare organizations face the challenge to deliver more patient care, of higher quality, and with less financial and human resources. The goal my doctoral thesis is to help and guide healthcare professionals making their organizations future-proof. The research presented contributes to a better understanding and functioning of healthcare delivery. In particular, the thesis intends to make healthcare professionals more aware of the added value of taking an integral perspective on logistical decision making. First, the problems addressed emphasize the importance of integrality in terms of objectives and performance. While the traditional belief is that quality and efficiency always confront each other, we demonstrate that they often can, and must, go hand in hand. Second, the research outcomes show the value of integrality in planning and control: performance is enhanced by aligning long-, medium-, and short-term decision making and by realizing coordination and collaboration between the various care chain actors. The results claim that taking an integral approach is the key to achieving what is reflected by the title of the dissertation: quality-driven efficiency.

EURO-Online login