Sensitivity Analysis of the OWA Operator

The successful design and application of the ordered weighted averaging (OWA) method as a decision-making tool depend on the efficient computation of its order weights. The most popular methods for determining the order weights are the fuzzy linguistic quantifiers approach and the minimal variabilit...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on cybernetics 2008-04, Vol.38 (2), p.547-552
Main Authors: Zarghami, M., Szidarovszky, F., Ardakanian, R.
Format: Article
Language:English
Subjects:
Algorithms
Civil engineering
Computational efficiency
Computer Simulation
Cybernetics
Decision making
Delta modulation
Fuzzy
Fuzzy linguistic quantifiers
Fuzzy Logic
Fuzzy set theory
Information Storage and Retrieval - methods
Linguistics
Mathematical model
Methods
minimal variability method
Models, Statistical
Neural networks
Open wireless architecture
Operations research
optimism degree
Optimization methods
ordered weighted averaging (OWA) operator
Pattern Recognition, Automated - methods
Reproducibility of Results
Resource management
Sensitivity analysis
Sensitivity and Specificity
Studies
Water resources
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The successful design and application of the ordered weighted averaging (OWA) method as a decision-making tool depend on the efficient computation of its order weights. The most popular methods for determining the order weights are the fuzzy linguistic quantifiers approach and the minimal variability method, which give different behavior patterns for the OWA. These two methods will be first analyzed in detail by using sensitivity analysis on the outputs of the OWA with respect to the optimism degree of the decision maker, and then the two methods will be compared. The fuzzy linguistic quantifiers approach gives more information about the behavior of the OWA outputs in comparison to the minimal variability method. However, in using the minimal variability method, the OWA has a linear behavior with respect to the optimism degree, and, therefore, it has better computation efficiency. Since maximizing the combined goodness measure and minimizing its sensitivity to optimism degree are conflicting objectives, a new composite measure of goodness will be defined to have more reliability in obtaining optimal solutions. The theoretical results will be illustrated in a water resources management problem.
ISSN:1083-4419
2168-2267
1941-0492
2168-2275
DOI:10.1109/TSMCB.2007.912745