Minimally Biased Nonparametric Regression and Autoregression
DOI:
https://doi.org/10.57805/revstat.v6i2.61Keywords:
nonparametric regression, autoregression, Fourier transformAbstract
A nonparametric regression estimator is introduced which adapts to the smoothness of the unknown function being estimated. This property allows the new estimator to automatically achieve minimal bias over a large class of locally smooth functions without changing the rate at which the variance converges. Optimal convergence rates are shown to hold for both i.i.d. data and autoregressive processes satisfying strong mixing conditions.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2008 REVSTAT-Statistical Journal
This work is licensed under a Creative Commons Attribution 4.0 International License.