In this paper, wavelet regression estimators are introduced, both in the random and the irregular design cases and without the restriction that the sample size is a power of two. A fast computational algorithm for approximating the empirical counterpart of the scaling and wavelet coefficients, is de
Random design wavelet curve smoothing
✍ Scribed by A. Antoniadis; G. Grégoire; P. Vial
- Publisher
- Elsevier Science
- Year
- 1997
- Tongue
- English
- Weight
- 387 KB
- Volume
- 35
- Category
- Article
- ISSN
- 0167-7152
No coin nor oath required. For personal study only.
✦ Synopsis
Common wavelet-based methods for nonparametric regression estimation are difficult to apply when the design is random. This paper proposes a modification of the linear wavelet estimator, called the binned wavelet estimator leading to a fast C(n) method with asymptotic properties identical with those of linear wavelet estimators under a fixed equidistant design. (~) 1997 Elsevier Science B.V.
📜 SIMILAR VOLUMES
We show that for nonparametric regression if the samples have random uniform design, the wavelet method with universal thresholding can be applied directly to the samples as if they were equispaced. The resulting estimator achieves within a logarithmic factor from the minimax rate of convergence ove
The wavelet threshold estimator of a regression function for the random design is constructed. The optimal uniform convergence rate of the estimator in a ball of Besov Space B s p, q is proved under general assumptions. The adaptive wavelet threshold estimator with near-optimal convergence rate in a
Straight-line and circular-arc segments with weight functions are used for interpolation. The smoothness of the curve depends on the weight functions. Variable smoothness can be achieved by changing the weights. The proposed technique is useful in robotics and numerically controlled machining, becau