Some advances on anchored ANOVA expansion for high order moments computation

Kunkun Tang (1) , Pietro Marco Congedo (1) , Rémi Abgrall (1)

1 BACCHUS - Parallel tools for Numerical Algorithms and Resolution of essentially Hyperbolic problems

Covariance decomposition of output variance is used in this paper to take account of interactions between non-orthogonal components in anchored ANOVA method. Results show this approach is less sensitive to the anchor reference point than existing method. Covariance-based sensitivity indices (SI) are also used, compared to variance-based SI. Furthermore, we emphasize covariance decomposition can be generalized in a straightforward way to decompose high order moments.

Mots clés: stochastic problems; uncertainty quantification; (anchored) ANOVA; global sensitivity analysis; variance/covariance decomposition

Domaines: Calcul [stat.CO]; Modélisation et simulation; Ingénierie, finance et science [cs.CE]

Kunkun Tang, Pietro Marco Congedo, Rémi Abgrall. Some advances on anchored ANOVA expansion for high order moments computation. 6th European Conference on Computational Fluid Dynamics (ECCOMAS CFD 2014), Jul 2014, Barcelona, Spain. ⟨hal-01054383⟩