Screening Important Inputs in Models with Strong Interaction Properties
We introduce a new method for screening inputs in mathematical or computational models with large numbers of inputs. The method proposed here represents an improvement over the best available practice for this setting when dealing with models having strong interaction effects. When the sample size is suffciently high the same design can also be used to obtain accurate quantitative estimates of
the variance-based sensitivity measures: the same simulations can be used to obtain estimates of the variance-based measures according to the Sobol' and the Jansen formulas. Results demonstrate that Sobol' is more effcient for the computation of the first order indices, while Jansen performs better for the computation of the total indices.
SALTELLI Andrea;
CAMPOLONGO Francesca;
CARIBONI Jessica;
2009-04-16
ELSEVIER SCI LTD
JRC49783
0951-8320,
https://publications.jrc.ec.europa.eu/repository/handle/JRC49783,
10.1016/j.ress.2008.10.007,
Additional supporting files
| File name | Description | File type | |
|---|
