The Annals of Probability
- Ann. Probab.
- Volume 37, Number 4 (2009), 1605-1646.
Uniform limit theorems for wavelet density estimators
Let pn(y)=∑kα̂kϕ(y−k)+∑l=0jn−1∑kβ̂lk2l/2ψ(2ly−k) be the linear wavelet density estimator, where ϕ, ψ are a father and a mother wavelet (with compact support), α̂k, β̂lk are the empirical wavelet coefficients based on an i.i.d. sample of random variables distributed according to a density p0 on ℝ, and jn∈ℤ, jn↗∞. Several uniform limit theorems are proved: First, the almost sure rate of convergence of sup y∈ℝ|pn(y)−Epn(y)| is obtained, and a law of the logarithm for a suitably scaled version of this quantity is established. This implies that sup y∈ℝ|pn(y)−p0(y)| attains the optimal almost sure rate of convergence for estimating p0, if jn is suitably chosen. Second, a uniform central limit theorem as well as strong invariance principles for the distribution function of pn, that is, for the stochastic processes , s∈ℝ, are proved; and more generally, uniform central limit theorems for the processes , , for other Donsker classes of interest are considered. As a statistical application, it is shown that essentially the same limit theorems can be obtained for the hard thresholding wavelet estimator introduced by Donoho et al. [Ann. Statist. 24 (1996) 508–539].
Ann. Probab., Volume 37, Number 4 (2009), 1605-1646.
First available in Project Euclid: 21 July 2009
Permanent link to this document
Digital Object Identifier
Mathematical Reviews number (MathSciNet)
Zentralblatt MATH identifier
Giné, Evarist; Nickl, Richard. Uniform limit theorems for wavelet density estimators. Ann. Probab. 37 (2009), no. 4, 1605--1646. doi:10.1214/08-AOP447. https://projecteuclid.org/euclid.aop/1248182150