Publication detail

Correlation in probabilistic simulation

VOŘECHOVSKÝ, M.

Original Title

Correlation in probabilistic simulation

Type

conference paper

Language

English

Original Abstract

The objective of this paper is twofold. Firstly to deliver theoretical bounds for performance of simulation techniques of Monte Carlo type measuring the ability to fulfill prescribed correlation matrices. Secondly, we study the performance in correlation control of recently proposed procedure for sampling from a multivariate population within the framework of Monte Carlo simulations (especially Latin Hypercube Sampling). In particular, we study the ability of the method to fulfill the prescribed correlation structure of a random vector for various sample sizes and number of marginal variables. Two norms of correlation error are defined, one very conservative and related to extreme errors, other related to averages of correlation errors. We study behavior of Pearson correlation coefficient for Gaussian vectors and Spearman rank order coefficient (as a distribution-free correlation measure). Theoretical results on performance bounds for both correlation types in the case of desired uncorrelatedness are compared to performance of the proposed technique and also to other previously developed techniques for correlation control.

Keywords

Correlation in probabilistic simulation

Authors

VOŘECHOVSKÝ, M.

RIV year

2011

Released

1. 8. 2011

Location

Zurich, Švýcarsko

ISBN

978-0-415-66986-3

Book

Applications of Statistics and Probability in Civil Engineering

Pages from

2931

Pages to

2939

Pages count

8

BibTex

@inproceedings{BUT88624,
  author="Miroslav {Vořechovský}",
  title="Correlation in probabilistic simulation",
  booktitle="Applications of Statistics and Probability in Civil Engineering",
  year="2011",
  pages="2931--2939",
  address="Zurich, Švýcarsko",
  isbn="978-0-415-66986-3"
}