Abstract
We present a comprehensive computational study on the effects of providing different forms of incomplete preference information in additive group
decision models. We consider different types of information on individual
preferences, and on weights of the group members, and study their effects on
conclusiveness, efficiency and fairness of outcomes at the group level. Furthermore, we analyze possible violations of the axiom of independence of
irrelevant alternatives (IIA) as well as the impact of problem characteristics,
in particular initial agreement between group members. Our results indicate
that providing information in the form of a ranking of differences between
consecutive alternatives comes close to providing exact cardinal preference
information in several outcome dimensions. However, group decision procedures based on incomplete preference information also show a significant
amount of violations of the IIA axiom.
decision models. We consider different types of information on individual
preferences, and on weights of the group members, and study their effects on
conclusiveness, efficiency and fairness of outcomes at the group level. Furthermore, we analyze possible violations of the axiom of independence of
irrelevant alternatives (IIA) as well as the impact of problem characteristics,
in particular initial agreement between group members. Our results indicate
that providing information in the form of a ranking of differences between
consecutive alternatives comes close to providing exact cardinal preference
information in several outcome dimensions. However, group decision procedures based on incomplete preference information also show a significant
amount of violations of the IIA axiom.
| Originalsprache | Englisch |
|---|---|
| Seiten (von - bis) | 160-171 |
| Seitenumfang | 12 |
| Fachzeitschrift | Computers & Operations Research |
| Jahrgang | 51 |
| DOIs | |
| Publikationsstatus | Veröffentlicht - Nov. 2014 |
ÖFOS 2012
- 502044 Unternehmensführung
- 101015 Operations Research