Verification validation and accreditation of simulation models
Proceedings of the 29th conference on Winter simulation
Validation in Simulation: Various Positions in the Philosophy of Science
Management Science
Computers and Intractability: A Guide to the Theory of NP-Completeness
Computers and Intractability: A Guide to the Theory of NP-Completeness
Verification and validation of simulation models
Proceedings of the Winter Simulation Conference
Hi-index | 0.00 |
The study of the complex relationship between simulation and reality is a defining characteristic that differentiates simulation science from science that uses simulation. Significant progress has been made toward a robust understanding of accuracy in this relationship. Although broadly accepted by the community as an important consideration, how a simulation is, or is to be, used has received less rigorous attention. Decision theory provides a mathematical structure to define use that is suitable to inform decision-making using models and simulations. Posed in this way, use is essentially formulated in the style of a decision problem within the context of theoretical computer science. While decision theory is useful to frame the decision problem, quantifying error remains as a key challenge that must be resolved before a meaningful evaluation of expected value or expected utility can be calculated. In this paper we demonstrate the use of Bayes Rule to update the probability estimates for the various outcomes framed in the decision problem, given a known simulation response, as additional evidence becomes available.