Multiple predictor smoothing methods for sensitivity analysis.
The use of multiple predictor smoothing methods in sampling-based sensitivity analyses of complex models is investigated. Specifically, sensitivity analysis procedures based on smoothing methods employing the stepwise application of the following nonparametric regression techniques are described: (1) locally weighted regression (LOESS), (2) additive models, (3) projection pursuit regression, and (4) recursive partitioning regression. The indicated procedures are illustrated with both simple test problems and results from a performance assessment for a radioactive waste disposal facility (i.e., the Waste Isolation Pilot Plant). As shown by the example illustrations, the use of smoothing procedures based on nonparametric regression techniques can yield more informative sensitivity analysis results than can be obtained with more traditional sensitivity analysis procedures based on linear regression, rank regression or quadratic regression when nonlinear relationships between model inputs and model predictions are present.
- Research Organization:
- Sandia National Laboratories
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC04-94AL85000
- OSTI ID:
- 893126
- Report Number(s):
- SAND2006-4693
- Country of Publication:
- United States
- Language:
- English
Similar Records
Projection pursuit regression
Projection pursuit regression
Generalized smooth models
Journal Article
·
Mon Nov 30 23:00:00 EST 1981
· J. Am. Stat. Assoc.; (United States)
·
OSTI ID:6232512
Projection pursuit regression
Conference
·
Thu Jan 31 23:00:00 EST 1980
·
OSTI ID:5632461
Generalized smooth models
Conference
·
Thu Jul 23 00:00:00 EDT 1992
·
OSTI ID:10157123