|
This article is cited in 3 scientific papers (total in 4 papers)
Short Communications
Online estimation of a smooth regression function
R. Sh. Liptsera, R. Z. Khas'minskiib a Tel Aviv University, Department of Electrical Engineering-Systems
b Wayne State University
Abstract:
The tracking (recursive) type estimator for a one-dimensional regression estimation problem with equidistant design is proposed. It is proven that, out of the inevitable initial layer, this estimator has the optimal rate of convergence of quadratic risk to zero if the sample size goes to infinity.
Keywords:
online tracking estimator, equidistant design, nonparametric estimation, regression.
Received: 04.09.2001
Citation:
R. Sh. Liptser, R. Z. Khas'minskii, “Online estimation of a smooth regression function”, Teor. Veroyatnost. i Primenen., 47:3 (2002), 567–575; Theory Probab. Appl., 47:3 (2003), 541–550
Linking options:
https://www.mathnet.ru/eng/tvp3696https://doi.org/10.4213/tvp3696 https://www.mathnet.ru/eng/tvp/v47/i3/p567
|
Statistics & downloads: |
Abstract page: | 326 | Full-text PDF : | 170 |
|