Download this Paper Open PDF in Browser

Copula Density Estimation by Total Variation Penalized Likelihood

Communications in Statistics – Simulation and Computation, Vol. 38, pp. 1891-1908, 2009

18 Pages Posted: 8 Dec 2009  

Leming Qu

affiliation not provided to SSRN

Yi Qian

Northwestern University - Kellogg School of Management

Hui Xie

University of Illinois

Date Written: September 3, 2009

Abstract

Copulas are full measures of dependence among random variables. They are increasingly popular among academics and practitioners in financial econometrics for modeling comovements between markets, risk factors, and other relevant variables. A copula’s hidden dependence structure that couples a joint distribution with its marginals makes a parametric copula non-trivial. An approach to bivariate copula density estimation is introduced that is based on a penalized likelihood with a total variation penalty term. Adaptive choice of the amount of egularization is based on approximate Bayesian Information Criterion (BIC) type scores. Performance are evaluated through the Monte Carlo simulation.

Keywords: Copula, Dependence modeling, Density estimation, Total variation

Suggested Citation

Qu, Leming and Qian, Yi and Xie, Hui, Copula Density Estimation by Total Variation Penalized Likelihood (September 3, 2009). Communications in Statistics – Simulation and Computation, Vol. 38, pp. 1891-1908, 2009. Available at SSRN: https://ssrn.com/abstract=1518628

Leming Qu (Contact Author)

affiliation not provided to SSRN

Yi Qian

Northwestern University - Kellogg School of Management ( email )

2001 Sheridan Road
Evanston, IL 60208
United States

Hui Xie

University of Illinois ( email )

1200 W Harrison St
Chicago, IL 60607
United States

Paper statistics

Downloads
81
Rank
259,034
Abstract Views
919