Correlation measures

Robustness and performance in simulations

Srinivas Sriramula, Devdas Menon, A. Meher Prasad

Research output: Contribution to conferencePaper

Abstract

Many civil engineering studies involve uncertainties arising at various levels and the rational modeling of such uncertainties requires effective simulation methods involving accurate dependencies. In this paper, the potential measures of dependence are described and their robustness is considered using the maximum bias estimates. The copula based multivariate distribution models are used in studying the bias at varying levels of data contamination with a point mass distribution. Two examples are considered pertinent to civil engineering applications and the database is considered to represent the classes of elliptical and non-elliptical marginal distribution combinations. The dependence measures are found to be biased depending on the marginal distribution type and the associated data scatter highlighting the need for appropriate dependence modelling in simulations. It is required to popularise the use of copula functions in engineering applications to consider the variable uncertainties effectively with the appropriate correlations.
Original languageEnglish
Number of pages6
Publication statusPublished - 2007
Event10th Int. Conf. on Applications of Statistics and Probability in Civil Engineering (ICASP10) - Tokyo, Japan
Duration: 31 Jul 2007 → …

Conference

Conference10th Int. Conf. on Applications of Statistics and Probability in Civil Engineering (ICASP10)
CountryJapan
CityTokyo
Period31/07/07 → …

Fingerprint

Civil Engineering
Copula
Marginal Distribution
Robustness
Engineering Application
Uncertainty
Measures of Dependence
Simulation
Multivariate Distribution
Scatter
Contamination
Modeling
Simulation Methods
Biased
Estimate
Model
Class

Keywords

  • simulations
  • product moment correlation
  • rank correlation
  • maximum bias curves
  • copula functions

Cite this

Sriramula, S., Menon, D., & Prasad, A. M. (2007). Correlation measures: Robustness and performance in simulations. Paper presented at 10th Int. Conf. on Applications of Statistics and Probability in Civil Engineering (ICASP10), Tokyo, Japan.

Correlation measures : Robustness and performance in simulations. / Sriramula, Srinivas; Menon, Devdas; Prasad, A. Meher.

2007. Paper presented at 10th Int. Conf. on Applications of Statistics and Probability in Civil Engineering (ICASP10), Tokyo, Japan.

Research output: Contribution to conferencePaper

Sriramula, S, Menon, D & Prasad, AM 2007, 'Correlation measures: Robustness and performance in simulations' Paper presented at 10th Int. Conf. on Applications of Statistics and Probability in Civil Engineering (ICASP10), Tokyo, Japan, 31/07/07, .
Sriramula S, Menon D, Prasad AM. Correlation measures: Robustness and performance in simulations. 2007. Paper presented at 10th Int. Conf. on Applications of Statistics and Probability in Civil Engineering (ICASP10), Tokyo, Japan.
Sriramula, Srinivas ; Menon, Devdas ; Prasad, A. Meher. / Correlation measures : Robustness and performance in simulations. Paper presented at 10th Int. Conf. on Applications of Statistics and Probability in Civil Engineering (ICASP10), Tokyo, Japan.6 p.
@conference{d381794d65b547609bb324db2f7313be,
title = "Correlation measures: Robustness and performance in simulations",
abstract = "Many civil engineering studies involve uncertainties arising at various levels and the rational modeling of such uncertainties requires effective simulation methods involving accurate dependencies. In this paper, the potential measures of dependence are described and their robustness is considered using the maximum bias estimates. The copula based multivariate distribution models are used in studying the bias at varying levels of data contamination with a point mass distribution. Two examples are considered pertinent to civil engineering applications and the database is considered to represent the classes of elliptical and non-elliptical marginal distribution combinations. The dependence measures are found to be biased depending on the marginal distribution type and the associated data scatter highlighting the need for appropriate dependence modelling in simulations. It is required to popularise the use of copula functions in engineering applications to consider the variable uncertainties effectively with the appropriate correlations.",
keywords = "simulations, product moment correlation, rank correlation, maximum bias curves, copula functions",
author = "Srinivas Sriramula and Devdas Menon and Prasad, {A. Meher}",
year = "2007",
language = "English",
note = "10th Int. Conf. on Applications of Statistics and Probability in Civil Engineering (ICASP10) ; Conference date: 31-07-2007",

}

TY - CONF

T1 - Correlation measures

T2 - Robustness and performance in simulations

AU - Sriramula, Srinivas

AU - Menon, Devdas

AU - Prasad, A. Meher

PY - 2007

Y1 - 2007

N2 - Many civil engineering studies involve uncertainties arising at various levels and the rational modeling of such uncertainties requires effective simulation methods involving accurate dependencies. In this paper, the potential measures of dependence are described and their robustness is considered using the maximum bias estimates. The copula based multivariate distribution models are used in studying the bias at varying levels of data contamination with a point mass distribution. Two examples are considered pertinent to civil engineering applications and the database is considered to represent the classes of elliptical and non-elliptical marginal distribution combinations. The dependence measures are found to be biased depending on the marginal distribution type and the associated data scatter highlighting the need for appropriate dependence modelling in simulations. It is required to popularise the use of copula functions in engineering applications to consider the variable uncertainties effectively with the appropriate correlations.

AB - Many civil engineering studies involve uncertainties arising at various levels and the rational modeling of such uncertainties requires effective simulation methods involving accurate dependencies. In this paper, the potential measures of dependence are described and their robustness is considered using the maximum bias estimates. The copula based multivariate distribution models are used in studying the bias at varying levels of data contamination with a point mass distribution. Two examples are considered pertinent to civil engineering applications and the database is considered to represent the classes of elliptical and non-elliptical marginal distribution combinations. The dependence measures are found to be biased depending on the marginal distribution type and the associated data scatter highlighting the need for appropriate dependence modelling in simulations. It is required to popularise the use of copula functions in engineering applications to consider the variable uncertainties effectively with the appropriate correlations.

KW - simulations

KW - product moment correlation

KW - rank correlation

KW - maximum bias curves

KW - copula functions

M3 - Paper

ER -