Abstract
Multi-criteria decision aid (MCDA) methods have been around for quite some time. However, the elicitation of preference information in MCDA processes, and in particular the lack of practical means supporting it, is still a significant problem in real-life applications of MCDA. There is obviously a need for methods that neither require formal decision analysis knowledge, nor are too cognitively demanding by forcing people to express unrealistic precision or to state more than they are able to. We suggest a method, the CAR method, which is more accessible than our earlier approaches in the field while trying to balance between the need for simplicity and the requirement of accuracy. CAR takes primarily ordinal knowledge into account, but, still recognizing that there is sometimes a quite substantial information loss involved in ordinality, we have conservatively extended a pure ordinal scale approach with the possibility to supply more information. Thus, the main idea here is not to suggest a method or tool with a very large or complex expressibility, but rather to investigate one that should be sufficient in most situations, and in particular better, at least in some respects, than some hitherto popular ones from the SMART family as well as AHP, which we demonstrate in a set of simulation studies as well as a large end-user study.
Similar content being viewed by others
Notes
We will henceforth, unless otherwise stated, presume that decision problems are modelled as simplexes \(S_{w}\) generated by \(w_{1}> w_{2}> \cdots > w_{N}, \Sigma w_{i}=1, \hbox { and } 0=w_{i}\).
To be more precise, a strict ordering is not required since ties are allowed.
In Danielson et al. (2014a) and Danielson and Ekenberg (2014b), ordinal weights are introduced that are more robust than other surrogate weights, in particular. Using steps 1–3 above, cardinal weights can analogously be obtained. This is explained in detail in Danielson and Ekenberg (2015) where the performance of a set of cardinal weights are compared to ordinal weights.
Sometimes there is a limit to the individual numbers but not a limit to the sum of the numbers.
A second success measure we used is the matching of the three highest ranked alternatives (“podium”), the number of times the three highest evaluated alternatives using a particular method all coincide with the true three highest alternatives. A third set generated is the matching of all ranked alternatives (“overall”), the number of times all evaluated alternatives using a particular method coincide with the true ranking of the alternatives. The two latter sets correlated strongly with the first and are not shown in this paper. Instead, we show the Kendall’s tau measure of overall performance.
SMART is represented by the improved SMARTER version by Edwards and Barron (1994).
AHP weights were derived by forming quotients \(\hbox {w}_{i}/\hbox {w}_{j}\) and rounding to the nearest odd integer. Also allowing even integers in between yielded no significantly better results.
The subjects had 2–4 years of university studies with no or little mathematical background. Thus, their level of education corresponds to an average decision making manager in many organisations.
References
Aguayo EA, Mateos A, Jiménez-Martín A (2014) A new dominance intensity method to deal with ordinal information about a DM’s preferences within MAVT. Knowl Based Syst 69:159–169
Ahn BS, Park KS (2008) Comparing methods for multiattribute decision making with ordinal weights. Comput Oper Res 35(5):1660–1670
Arbel A, Vargas LG (1993) Preference simulation and preference programming: robustness issues in priority derivation. Eur J Oper Res 69:200–209
Bana e Costa CA, Vansnick JC (1999) The MACBETH approach: basic ideas, software, and an application. In: Meskens N, Roubens M (eds) Advances in decision analysis, vol 4., Mathematical modelling: theory and applicationsKluwer Academic Publishers, Dordrecht, pp 131–157
Bana e Costa CA, Correa EC, De Corte JM, Vansnick JC (2002) Facilitating bid evaluation in public call for tenders: a socio-technical approach. Omega 30:227–242
Barron FH (1992) Selecting a best multiattribute alternative with partial information about attribute weights. Acta Psychol 80(1–3):91–103
Barron F, Barrett B (1996a) The efficacy of SMARTER: simple multi-attribute rating technique extended to ranking. Acta Psychol 93(1–3):23–36
Barron F, Barrett B (1996b) Decision quality using ranked attribute weights. Manag Sci 42(11):1515–1523
Belton V, Gear T (1983) On a short-coming of Saaty’s method of analytic hierarchies. Omega 11(3):228–230
Belton V, Stewart T (2002) Multiple criteria decision analysis: an integrated approach. Kluwer Academic Publishers, Dordrecht
Bisdorff R, Dias LC, Meyer P, Mousseau V, Pirlot M (eds) (2015) Evaluation and decision models with multiple criteria: case studies. Springer, Berlin
Brans JP, Vincke PH (1985) A preference ranking organization method: the PROMETHEE method. Manag Sci 31:647–656
Butler J, Jia J, Dyer J (1997) Simulation techniques for the sensitivity analysis of multi-criteria decision models. Eur J Oper Res 103:531–546
Cook W, Kress M (1996) An extreme-point approach for obtaining weighted ratings in qualitative multicriteria decision making. Naval Res Logist 43:519–531
Danielson M, Ekenberg L (1998) A framework for analysing decisions under risk. Eur J Oper Res 104(3):474–484
Danielson M, Ekenberg L (2007) Computing upper and lower bounds in interval decision trees. Eur J Oper Res 181(2):808–816
Danielson M, Ekenberg L, He Y (2014a) Augmenting ordinal methods for attribute weight approximations. Decis Anal 11(1):21–26
Danielson M, Ekenberg L (2014b) Rank ordering methods for multi-criteria decisions. In: Proceedings of 14th group decision and negotiation—GDN 2014, Springer
Danielson M, Ekenberg L (2015) Using surrogate weights for handling preference strength in multi-criteria decisions. In: Proceedings of 15th group decision and negotiation—GDN 2015, Springer
Danielson M, Ekenberg L, Johansson J, Larsson A (2003) The DecideIT decision tool. In: Bernard J-M, Seidenfeld T, Zaffalon M (eds) Proceedings of ISIPTA’03, pp 204–217, Carleton Scientific
Danielson M, Ekenberg L, Larsson A (2007) Distribution of belief in decision trees. Int J Approx Reason 46(2):387–407
Danielson M, Ekenberg L, Riabacke A (2009) A prescriptive approach to elicitation of decision data. J Stat Theory Pract 3(1):157–168
Danielson M, Ekenberg L, Larsson A, Riabacke M (2014) Weighting under ambiguous preferences and imprecise differences in a cardinal rank ordering process. Int J Comput Intell Syst 7(1):105–112
Devroye L (1986) Non-uniform random variate generation. Springer, Berlin
Dias LC, Clímaco JN (2000) Additive aggregation with variable interdependent parameters: the VIP analysis software. J Oper Res Soc 51(9):1070–1082
Ekenberg L, Boman M, Danielson M (1995) A tool for coordinating autonomous agents with conflicting goals. In: Proceedings of the 1st international conference on multi-agent systems ICMAS ’95, pp 89–93, AAAI/MIT Press
Ekenberg L, Boman M, Linneroth-Bayer J (2001a) General risk constraints. J Risk Res 4(1):31–47
Ekenberg L, Danielson M, Larsson A, Sundgren D (2014) Second-order risk constraints in decision analysis. Axioms 3:31–45. doi:10.3390/axioms3010031
Ekenberg L, Thorbiörnson J (2001) Second-order decision analysis. Int J Uncertain Fuzziness Knowl Based Syst 9(1):13–38
Ekenberg L, Thorbiörnson J, Baidya T (2005) Value differences using second order distributions. Int J Approx Reason 38(1):81–97
Edwards W (1971) Social utilities. In: Engineering economist, summer symposium series, vol 6, pp 119–129
Edwards W (1977) How to use multiattribute utility measurement for social decisionmaking. IEEE Trans Syst Man Cybern 7(5):326–340
Edwards W, Barron F (1994) SMARTS and SMARTER: improved simple methods for multiattribute utility measurement. Organ Behav Hum Decis Process 60:306–325
Figueira J, Roy B (2002) Determining the weights of criteria in the ELECTRE type methods with a revised Simos’ procedure. Eur J Oper Res 139:317–326
Ginevicius R (2009) A new determining method for the criteria weights in multicriteria evaluation. Int J Inf Technol Decis Making 10(6):1067–1095
Jia J, Fischer GW, Dyer J (1998) Attribute weighting methods and decision quality in the presence of response error: a simulation study. J Behav Decis Making 11(2):85–105
Jiménez A, Ríos-Insua S, Mateos A (2006) A generic multi-attribute analysis system. Comput Oper Res 33:1081–1101
Katsikopoulos K, Fasolo B (2006) New tools for decision analysis. IEEE Trans Syst Man Cybern A Syst Hum 36(5):960–967
Keeney R, Raiffa H (1976) Decisions with multiple objectives: preferences and value tradeoffs. Wiley, New York
Kirkwood CW (1997) strategic decision making: multiobjective decision making with spreadsheets. Wadsworth Publishing, Belmont
Krovak J (1987) Ranking alternatives-comparison of different methods based on binary comparison matrices. Eur J Oper Res 32:86–95
Larsson A, Johansson J, Ekenberg L, Danielson M (2005) Decision analysis with multiple objectives in a framework for evaluating imprecision. Int J Uncertain Fuzziness Knowl Based Syst 13(5):495–509
Larsson A, Riabacke M, Danielson M, Ekenberg L (2014) Cardinal and rank ordering of criteria—addressing prescription within weight elicitation. Int J Inf Technol Decis Making. doi:10.1142/S021962201450059X
Mateos A, Jiménez-Martín A, Aguayo EA, Sabio P (2014) Dominance intensity measuring methods in MCDM with ordinal relations regarding weights. Knowl Based Syst 70:26–32
Milnor J (1954) Games against nature. In: Thrall RM, Coombs CH, Davies RL (eds) Decision processes. Wiley
Mustajoki J, Hämäläinen R (2005) A preference programming approach to make the even swaps method even easier. Decis Anal 2:110–123
Mustajoki J, Hämäläinen R, Salo A (2005) Decision support by interval SMART/SWING—incorporating imprecision in the SMART and SWING methods. Decis Sci 36(2):317–339
Park KS (2004) Mathematical programming models for characterizing dominance and potential optimality when multicriteria alternative values and weights are simultaneously incomplete. IEEE Trans Syst Man Cybern A Syst Hum 34(5):601–614
Puerto J, Mármol AM, Monroy L, Fernández FR (2000) Decision criteria with partial information. Int Trans Oper Res 7:51–65
Rao JS, Sobel M (1980) Incomplete Dirichlet integrals with applications to ordered uniform spacing. J Multivar Anal 10:603–610
Riabacke M, Danielson M, Ekenberg L (2012) State-of-the-art in prescriptive weight elicitation. Adv Decis Sci. doi:10.1155/2012/276584
Roberts R, Goodwin P (2002) Weight approximations in multi-attribute decision models. J Multi Criteria Decis Anal 11:291–303
Roy B (1968) Classement et choix en présence de points de vue multiples (la méthode ELECTRE). La Revue d’Informatique et de Recherche Opérationelle 8:57–75
Saaty TL (1977) A scaling method for priorities in hierarchical structures. J Math Psychol 15:234–281
Saaty TL (1980) The analytic hierarchy process. McGraw-Hill, New York
Salo AA, Hämäläinen RP (2001) Preference ratios in multiattribute evaluation (PRIME)–elicitation and decision procedures under incomplete information. IEEE Trans Syst Man Cybern A Syst Hum 31:533–545
Sarabando P, Dias L (2009) Multi-attribute choice with ordinal information: a comparison of different decision rules. IEEE Trans Syst Man Cybern A 39:545–554
Sarabando P, Dias L (2010) Simple procedures of choice in multicriteria problems without precise information about the alternatives’ values. Comput Oper Res 37:2239–2247
Steuer RE (1984) Sausage blending using multiple objective linear programming. Manag Sci 30(11):1376–1384
Stewart TJ (1993) Use of piecewise linear value functions in interactive multicriteria decision support: a Monte Carlo study. Manag Sci 39(11):1369–1381
Stillwell W, Seaver D, Edwards W (1981) A comparison of weight approximation techniques in multiattribute utility decision making. Organ Behav Hum Perform 28(1):62–77
von Winterfeldt D, Edwards W (1986) Decision analysis and behavioural research. Cambridge University Press, Cambridge
Winkler RL, Hays WL (1985) Statistics: probability, inference and decision, Holt. Rinehart & Winston, New York
Acknowledgments
This research was funded by the Swedish Research Council FORMAS, Project Number 2011-3313-20412-31, as well as by Strategic funds from the Swedish government within ICT—The Next Generation.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest
The authors declare that they have no conflict of interest.
Rights and permissions
About this article
Cite this article
Danielson, M., Ekenberg, L. The CAR Method for Using Preference Strength in Multi-criteria Decision Making. Group Decis Negot 25, 775–797 (2016). https://doi.org/10.1007/s10726-015-9460-8
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10726-015-9460-8