Cross validation for locally stationary processes
Statistics Theory
2017-05-30 v1 Statistics Theory
Abstract
We propose an adaptive bandwidth selector via cross validation for local M-estimators in locally stationary processes. We prove asymptotic optimality of the procedure under mild conditions on the underlying parameter curves. The results are applicable to a wide range of locally stationary processes such linear and nonlinear processes. A simulation study shows that the method works fairly well also in misspecified situations.
Cite
@article{arxiv.1705.10046,
title = {Cross validation for locally stationary processes},
author = {Stefan Richter and Rainer Dahlhaus},
journal= {arXiv preprint arXiv:1705.10046},
year = {2017}
}
Comments
67 pages (28 main article, 39 appendix), 2 figures