Wavelet regression estimation over L-p risk based on negatively associated sample

摘要

This paper considers wavelet estimations of a regression function based on negatively associated sample. We provide upper bound estimations over L-p(1 <= p < infinity) risk of linear and nonlinear wavelet estimators in Resov space, respectively. When the random sample reduces to the independent case, our convergence rates coincide with the optimal convergence rates of classical nonparametric regression estimation.