Minimax A- and D-optimal Integer-Valued Wavelet Designs for Estimation Abbreviated title: Minimax A- and D-optimal Wavelet Designs
نویسنده
چکیده
In this study we discuss integer-valued designs for wavelet estimation of nonparametric response curves in the possible presence of heteroscedastic noise based on a modi ̄ed wavelet version of the Gasser-MÄ uller kernel estimator and weighted least squares estimation. The Gasser-MÄ uller estimator was modi ̄ed in order to obtain an exact expression for the bias of the estimator. We ̄rst use data simulated from three curves to demonstrate that these estimators are °exible enough to e®ectively estimate nonparametric curves. Then, using a minimax treatment and the simulated annealing algorithm, we construct integer-valued designs for wavelet estimation of nonparametric curves. We present some examples involving the Daubechies and the multiwavelet systems. We discuss designs for three case studies on an experiment to investigate Gompertz theory, nitrite utilization in bush beans and the motorcycle impact experiment.
منابع مشابه
Minimax A- and D-optimal integer-valued wavelet designs for estimation
Abstract: The author discusses integer-valued designs for wavelet estimation of nonparametric response curves in the possible presence of heteroscedastic noise using a modified wavelet version of the Gasser– Müller kernel estimator or weighted least squares estimation. The designs are constructed using a minimax treatment and the simulated annealing algorithm. The author presents designs for th...
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 کاملInteger-Valued Designs and Wavelet Versions of Nonparametric Curve Estimators Abbreviated title: Wavelet Curve Estimation
In this article, we discuss wavelet versions of nonparametric curve estimators and weighted least squares wavelet regression. We introduce a modi ̄ed wavelet version of the Gasser-MÄ uller estimator that is unbiased whenever a wavelet representation of the nonparametric response curve correctly speci ̄es the response. In some cases, involving the Daubechies wavelet system, we ̄nd that the modi ̄ed ...
متن کاملNew criteria for robust integer-valued designs in linear models
We investigate the problem of designing for linear regression models, when the assumed model form is only an approximation to an unknown true model, using two novel approaches. The first is based on a notion of averaging of the mean-squared error of predictions over a neighbourhood of contaminating functions. The other is based on the usual D-optimal criterion but subject to bias-related constr...
متن کاملExistence and symmetry of minimax regression designs
In this paper we address two important issues about minimax regression designs: existence and symmetry. These designs are robust against possible misspecification of the regression response. Existence is proved for A-optimal, D-optimal and Q-optimal minimax designs. Symmetry is proved for all D-optimal minimax designs and for some special cases of A-optimal and Q-optimal minimax designs.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2001