English

Calculating correlation coefficient for Gaussian copula

Methodology 2016-08-03 v1

Abstract

When Gaussian copula with linear correlation coefficient is used to model correlated random variables, one crucial issue is to determine a suitable correlation coefficient ρz\rho_z in normal space for two variables with correlation coefficient ρx\rho_x. This paper attempts to address this problem. For two continuous variables, the marginal transformation is approximated by a weighted sum of Hermite polynomials, then, with Mehler's formula, a polynomial of ρz\rho_z is derived to approximate the function relationship between ρx\rho_x and ρz\rho_z. If a discrete variable is involved, the marginal transformation is decomposed into piecewise continuous ones, and ρx\rho_x is expressed as a polynomial of ρz\rho_z by Taylor expansion. For a given ρx\rho_x, ρz\rho_z can be efficiently determined by solving a polynomial equation.

Cite

@article{arxiv.1608.00738,
  title  = {Calculating correlation coefficient for Gaussian copula},
  author = {Qing Xiao},
  journal= {arXiv preprint arXiv:1608.00738},
  year   = {2016}
}
R2 v1 2026-06-22T15:09:52.117Z