Variance Decomposition in the Presence of Epistemic and Aleatory Uncertainty John McFarland and David Riha Abstract Variance-based global sensitivity analysis is a powerful approach for understanding the importance of model input variables or groups of variables in driving model output variation. However, input variance is often attributable to both aleatory (irreducible) and epistemic (reducible) uncertainties. This paper presents an approach whereby variance decomposition is used in conjunction with probabilistic analysis. Epistemic uncertainty associated with a model’s probabilistic response is decomposed based on probability distribution uncertainty, deterministic model uncertainty, and other epistemic uncertainty sources. The proposed methodology allows for the identification of the epistemic uncertainty sources having the largest contributions to the uncertainty in the model’s response. As demonstrated in the numerical example, the proposed methodology may be used to support resource allocation decisions in modeling and simulation activities. 1 Introduction Probabilistic methods are now commonly used in modeling and simulation activities as a means for taking account of variations and uncertainties associated with model inputs. Many practitioners are aware of the theoretical distinction that is commonly made between two types of uncertainty (aleatory uncertainty and epistemic uncertainty). However, the importance of the distinction, and the implications it has for performing a probabilistic analysis are often unclear. This paper will present some ideas regarding the roles that aleatory and epistemic uncertainty may play in a probabilistic analysis (in particular, a probabilistic J.M. McFarland Research Engineer, Southwest Research Institute, 6220 Culebra Rd., San Antonio, TX 78238 D.S. Riha Principal Engineer, Southwest Research Institute T. Proulx (ed.), Linking Models and Experiments, Volume 2, Conference Proceedings of the Society for Experimental Mechanics Series 5, 417 DOI 10.1007/978-1-4419-9305-2_32, © The Society for Experimental Mechanics, Inc. 2011
RkJQdWJsaXNoZXIy MTMzNzEzMQ==