The Bayesian Compromise Decision Support Problem for Multilevel Design Involving Uncertainty

Abstract

In this paper we present an extension to the traditional compromise Decision Support Problem (DSP) formulation. In this formulation we use Bayesian statistics to model uncertainties associated with the information being used. In an earlier paper we have introduced a compromise DSP that accounts for uncertainty using fuzzy set theory. In this paper we describe the Bayesian Decision Support Problem. We use this formulation to design a portal frame structure. We discuss the results and compare them with those obtained using the fuzzy DSP. Finally, we discuss the efficacy of incorporating Bayesian statistics into the traditional compromise DSP formulation and describe some of the pending research issues.