Theme 3 (old):
Qualitative Sensitivity Analysis

Abstract

We introduce the Qualitative Sensitivity Analysis (QSA) technique and its applications for systems modeled in rule based causal format. The rule set is composed of interacting atomic propositions. First, we introduce the Modified Causal Ordering (MCO) technique to derive ordering among the propositions. The result of MCO are complete subsets of propositions and an Ordinal Reachability Graph (ORG). Each complete subset is identified by its ranking code. In QSA, propositions stand for the landmarks of the qualitative variables. QSA begins with the ORG and replaces the propositions with their equivalent landmarks. Sensitivity is defined qualitatively in terms of possible shift to the neighboring landmarks. QSA can derive the sensitivity of the higher rank landmarks due to perturbation affecting the lower rank ones. Here we introduce the application of QSA for performance evaluation of discrete event dynamic systems (DEDS) and also generating diagnostic rules for concurrent malfunctions in rule based systems. We demonstrate the approach through two detailed illustrative examples.