Efficient Estimation of the High Dimensional Model Representation for Non-Linear Models (PSAM-0402)


In this paper we review an approach to the estimation of the High Dimensional Model Representation (HDMR) of non-linear models based of State Dependent Parameter (SDP) modeling (a model estimation approach, based on recursive filtering and smoothing estimation, see [1]). The method is conceptually simple and all measures of interest are computed using a single set of model runs. It is flexible because in principle it can be applied with any available type of Monte Carlo sample. It is extremely efficient and it allows for a strong reduction in the cost of the analysis. It involves a preliminary study of parameters sensitivity using wavelet decomposition. The applicability of the present method ranges from the computation of variance based sensitivity indices to the more general framework of a statistical approximation of a computer code and can be therefore considered in the wider context of meta-modeling or emulation, through which any measure of interest can be computed, based on the meta-model.

  • Summary/Abstract
  • Introduction
  • 1. Factor Priorization Using Wavelets
  • 2. SDP Models and HDMR
  • 3. Applications
  • References

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In