Integration of ordinal and cardinal information in multi-criteria ranking with imperfect compensation
- 16 October 2004
- journal article
- Published by Elsevier BV in European Journal of Operational Research
- Vol. 158 (2), 317-338
- https://doi.org/10.1016/j.ejor.2003.06.007
Abstract
The method presented in this paper is a MCDA method, which outranks a certain number of choice options that are evaluated on a mixture of cardinal and ordinal judgement criteria. Characteristics of the method are a theoretically sound integration of cardinal and ordinal information and a decision-makers' preference structure that allows for less than perfect compensation between criteria. The method is based on a pairwise comparison of choice-options. It belongs to the family of decomposed scaling methods: the assessment of the relative importance of the criteria on one hand and the assessment of the scores (cardinal criteria) and rankings (ordinal criteria) on the other hand are performed separately. The assessment of the scores and rankings is realised by means of (marginal) value functions in such a way that the ordinal information is fully comparable with the cardinal information. Essentially, the ordinal information is translated into stochastical information without imposing any assumption on the probability distributions attached to the ordinal data. The relative importance of the judgement criteria is represented by a set of cardinal weights or by a ranking of weights. The final ranking of the choice options is based upon an overall value function that is some kind of weighed aggregation of the marginal value functions. In order to allow for less-than-perfect-compensation between criteria, the method uses a convex combination of two different CES-type value functions. The paper ends with an empirical application, on the planning of public transport systems in The Netherlands. © 2003 Elsevier B.V. All rights reservedKeywords
This publication has 8 references indexed in Scilit:
- Ranking Alternatives on the Basis of Preference Relations: A Progress Report with Special Emphasis on Outranking RelationsJournal of Multi-Criteria Decision Analysis, 1997
- Outranking Relations: Do They Have Special Properties?Journal of Multi-Criteria Decision Analysis, 1996
- A Theoretical Framework for Analysing the Notion of Relative Importance of CriteriaJournal of Multi-Criteria Decision Analysis, 1996
- Ordinal data in multicriteria decision making, a stochastic dominance approach to siting nuclear power plantsEuropean Journal of Operational Research, 1992
- Qualitative multiple criteria choice analysisQuality & Quantity, 1990
- Qualitative discrete multiple criteria choice models in regional planningRegional Science and Urban Economics, 1983
- Qualiflex: A flexible multiple-criteria methodEconomics Letters, 1978
- A nested CES-type utility function and its demand and price-index functionsEuropean Economic Review, 1976