Where academic tradition
meets the exciting future

You are here: TUCS > PUBLICATIONS > Publication Search > Two ways to handle dependent u...

Two ways to handle dependent uncertainties in multi-criteria decision problems

Risto Lahdelma, Simo Makkonen, Pekka Salminen, Two ways to handle dependent uncertainties in multi-criteria decision problems. Omega 37(1), 79-92, 2009.

Abstract:

We consider multi-criteria group decision-making problems, where the decision makers (DMs) want to identify their most
preferred alternative(s) based on uncertain or inaccurate criteria measurements. In many real-life problems the uncertainties may be
dependent. In this paper, we focus on multicriteria decision-making (MCDM) problems where the criteria and their uncertainties
are computed using a stochastic simulation model. The model is based on decision variables and stochastic parameters with given
distributions. The simulation model determines for the criteria a joint probability distribution, which quantifies the uncertainties
and their dependencies. We present and compare two methods for treating the uncertainty and dependency information within
the SMAA-2 multi-criteria decision aid method. The first method applies directly the discrete sample generated by the simulation
model. The second method is based on using a multivariate Gaussian distribution. We demonstrate the methods using a decision
support model for a retailer operating in the deregulated European electricity market.

BibTeX entry:

@ARTICLE{jLaMaSa09a,
  title = {Two ways to handle dependent uncertainties in multi-criteria decision problems},
  author = {Lahdelma, Risto and Makkonen, Simo and Salminen, Pekka},
  journal = {Omega},
  volume = {37(1)},
  pages = {79-92},
  year = {2009},
  keywords = {Multicriteria; Decision making; Simulation; Group decisions; Energy; Risk},
}

Belongs to TUCS Research Unit(s): Algorithmics and Computational Intelligence Group (ACI)

Edit publication