Block thresholding wavelet estimation of copula density based on NSD assumption

Abstract

In this article, we consider the wavelet estimation of copula density for negatively superadditive dependent random variables. Using wavelet methods, we propose and develop a new estimation procedure for this problem. In particular, a BlockShrink estimator is constructed and we prove that it enjoys powerful mean integrated squared error properties over Besov balls. The main result is prepared to display the performance of the wavelet-based estimator and a simulation study to compare the behavior of the proposed wavelet estimator with the kernel copula density estimator are also given. Finally, we consider a real life application in hydrology for rainfall intensity data.