Proportional marginal effects for global sensitivity analysis - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

Proportional marginal effects for global sensitivity analysis

Résumé

Performing (variance-based) global sensitivity analysis (GSA) with dependent inputs has recently benefited from cooperative game theory concepts. By using this theory, despite the potential correlation between the inputs, meaningful sensitivity indices can be defined via allocation shares of the model output's variance to each input. The ``Shapley effects'', i.e., the Shapley values transposed to variance-based GSA problems, allowed for this suitable solution. However, these indices exhibit a particular behavior that can be undesirable: an exogenous input (i.e., which is not explicitly included in the structural equations of the model) can be associated with a strictly positive index when it is correlated to endogenous inputs. In the present work, the use of a different allocation, called the ``proportional values'' is investigated. A first contribution is to propose an extension of this allocation, suitable for variance-based GSA. Novel GSA indices are then proposed, called the ``proportional marginal effects'' (PME). The notion of exogeneity is formally defined in the context of variance-based GSA, and it is shown that the PME allow the distinction of exogenous variables, even when they are correlated to endogenous inputs. Moreover, their behavior is compared to the Shapley effects on analytical toy-cases and more realistic use-cases.
Fichier principal
Vignette du fichier
PME_preprint.pdf (2.15 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03825935 , version 1 (23-10-2022)
hal-03825935 , version 2 (30-05-2023)
hal-03825935 , version 3 (30-10-2023)
hal-03825935 , version 4 (16-03-2024)

Identifiants

Citer

Margot Herin, Marouane Il Idrissi, Vincent Chabridon, Bertrand Iooss. Proportional marginal effects for global sensitivity analysis. 2022. ⟨hal-03825935v1⟩
245 Consultations
103 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More