We explore the tasks where sensitivity analysis (SA) can be useful
and try to assess the relevance of SA within the modeling process. We suggest
that SA could considerably assist in the use of models, by providing objective
criteria of judgement for different phases of the modelbuilding
process: model identification and discrimination; model calibration; model
corroboration.
¶ We review some new global quantitative SA methods and suggest that
these might enlarge the scope for sensitivity analysis in computational and
statistical modeling practice. Among the advantages of the new methods are
their robustness, model independence and computational convenience.
¶ The discussion is based on worked examples.
Publié le : 2000-11-01
Classification:
Global sensitivity analysis,
quantitative sensitivity measure,
screening,
numerical experiments,
predictive uncertainty,
reliability and dependability of models,
model transparency
@article{1009213004,
author = {Saltelli, A. and Tarantola, S. and Campolongo, F.},
title = {Sensitivity Anaysis as an Ingredient of Modeling},
journal = {Statist. Sci.},
volume = {15},
number = {1},
year = {2000},
pages = { 377-395},
language = {en},
url = {http://dml.mathdoc.fr/item/1009213004}
}
Saltelli, A.; Tarantola, S.; Campolongo, F. Sensitivity Anaysis as an Ingredient of Modeling. Statist. Sci., Tome 15 (2000) no. 1, pp. 377-395. http://gdmltest.u-ga.fr/item/1009213004/