Non-parametric Estimation of Conditional Moments for Sensitivity Analysis
In this paper we deal with the non-parametric estimation of conditional moments, useful for applications in global sensitivity analysis (GSA) and in the more general emulation framework. The estimation is based on the State Dependent Parameter (SDP) modelling approach. The estimation of conditional moments of order larger than one allows to identify a wider spectrum of parameter sensitivities with respect to the variance based main effects, like shifts in the variance, skewness or kurtosis of the model output, adding valuable information for the analyst at a small computational cost.
RATTO Marco;
PAGANO Andrea;
YOUNG Peter C.;
2009-01-05
ELSEVIER SCI LTD
JRC44224
0951-8320,
http://dx.doi.org/10.1016/j.ress.2008.02.023,
https://publications.jrc.ec.europa.eu/repository/handle/JRC44224,
10.1016/j.ress.2008.02.023,
Additional supporting files
| File name | Description | File type | |
|---|
