Adaptive wavelet estimator for nonparametric density deconvolution
MetadataShow full item record
The problem of estimating a density g based on a sample X ₁ X ₂,…,X [subscript n] from p = q ∗ g is considered. Linear and nonlinear wavelet estimators based on Meyer-type wavelets are constructed. The estimators are asymptotically optimal and adaptive if g belongs to the Sobolev space H[superscript α].Moreover, the estimators considered in this paper adjust automatically to the situation when g is supersmooth.