Abstract
In this paper, we consider the non-parametric estimation of the copula density under biased data. The contributions are both theoretical and practical. In the first part, we propose and develop a new wavelet-based methodology 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 second part is devoted to the applied aspect: we compare the performance of the wavelet-based estimator with that of a recently introduced kernel-based estimator through a detailed simulation study.
Full Text
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call