Statistical Preconditioning in Simulation of Stochastic Vectors

by Fumio Yamazaki, Univ of Tokyo, Japan,
Masanobu Shinozuka, Univ of Tokyo, Japan,



Document Type: Proceeding Paper

Part of: Structural Safety and Reliability

Abstract:

A new stochastic vector simulation technique which realizes prescribed zero-mean vector and covariance matrix with a substantially smaller sample size than that of other existing methods has developed. The method utilizes the modal decomposition of the covariance matrix and the spectral representation of random processes. The ensemble-averaged means and covariance matrix and sample distribution by the proposed method are most favorably compared with those by the standard method.

Subject Headings: Stochastic processes | Statistics | Vector analysis | Matrix (mathematics) | Probability | Monte Carlo method | Decomposition

Services: Buy this book/Buy this article

 

Return to search