Asymptotic Minimaxity of Wavelet Estimators with Sampled Data
نویسندگان
چکیده
Donoho and Johnstone (1997) studied a setting where data were obtained in the continuum white noise model and showed that scalar nonlinearities applied to wavelet coefficients gave estimators which were asymptotically minimax over Besov balls. They claimed that this implied similar asymptotic minimaxity results in the sampleddata model. In this paper we carefully develop and fully prove this implication. Our results are based on a careful definition of an empirical wavelet transform and precise bounds on the discrepancy between empirical wavelet coefficiets and the theoretical wavelet coefficients.
منابع مشابه
On Block Thresholding in Wavelet Regression with Long Memory Correlated Noise
Johnstone and Silverman (1997) and Johnstone (1999) described a level-dependent thresholding method for extracting signals from both shortand long range dependent noise in the wavelet domain structure. It is shown that their Stein unbiased risk estimators (SURE) attain the exact optimal convergence rates in a wide range of Besov balls in certain asymptotic models of standard sample-data models....
متن کاملOn the Minimax Optimality of Block Thresholded Wavelets Estimators for ?-Mixing Process
We propose a wavelet based regression function estimator for the estimation of the regression function for a sequence of ?-missing random variables with a common one-dimensional probability density function. Some asymptotic properties of the proposed estimator based on block thresholding are investigated. It is found that the estimators achieve optimal minimax convergence rates over large class...
متن کاملMinimax Estimation with Thresholding and Its Application to Wavelet Analysis by Harrison
Many statistical practices involve choosing between a full model and reduced models where some coefficients are reduced to zero. Data were used to select a model with estimated coefficients. Is it possible to do so and still come up with an estimator always better than the traditional estimator based on the full model? The James–Stein estimator is such an estimator, having a property called min...
متن کاملMinimax Estimation with Thresholding and Its Application to Wavelet Analysis
Many statistical practices involve choosing between a full model and reduced models where some coefficients are reduced to zero. Data were used to select a model with estimated coefficients. Is it possible to do so and still come up with an estimator always better than the traditional estimator based on the full model? The James–Stein estimator is such an estimator, having a property called min...
متن کاملAsymptotic Distributions of Estimators of Eigenvalues and Eigenfunctions in Functional Data
Functional data analysis is a relatively new and rapidly growing area of statistics. This is partly due to technological advancements which have made it possible to generate new types of data that are in the form of curves. Because the data are functions, they lie in function spaces, which are of infinite dimension. To analyse functional data, one way, which is widely used, is to employ princip...
متن کامل