Translator Disclaimer
2020 Modeling of time series using random forests: Theoretical developments
Richard A. Davis, Mikkel S. Nielsen
Electron. J. Statist. 14(2): 3644-3671 (2020). DOI: 10.1214/20-EJS1758

Abstract

In this paper we study asymptotic properties of random forests within the framework of nonlinear time series modeling. While random forests have been successfully applied in various fields, the theoretical justification has not been considered for their use in a time series setting. Under mild conditions, we prove a uniform concentration inequality for regression trees built on nonlinear autoregressive processes and, subsequently, we use this result to prove consistency for a large class of random forests. The results are supported by various simulations.

Citation

Download Citation

Richard A. Davis. Mikkel S. Nielsen. "Modeling of time series using random forests: Theoretical developments." Electron. J. Statist. 14 (2) 3644 - 3671, 2020. https://doi.org/10.1214/20-EJS1758

Information

Received: 1 August 2020; Published: 2020
First available in Project Euclid: 6 October 2020

zbMATH: 07270273
MathSciNet: MR4159176
Digital Object Identifier: 10.1214/20-EJS1758

Subjects:
Primary: 62G05
Secondary: 60G10, 60J05, 62G08, 62M05, 62M10

JOURNAL ARTICLE
28 PAGES


SHARE
Vol.14 • No. 2 • 2020
Back to Top