Cookies?
Library Header Image
LSE Research Online LSE Library Services

An autocovariance-based learning framework for high-dimensional functional time series

Chang, Jinyuan, Chen, Cheng, Qiao, Xinghao ORCID: 0000-0002-6546-6595 and Yao, Qiwei ORCID: 0000-0003-2065-8486 (2023) An autocovariance-based learning framework for high-dimensional functional time series. Journal of Econometrics. ISSN 0304-4076

[img] Text (An autocovariance-based learning framework for high-dimensional time series) - Accepted Version
Pending embargo until 1 January 2100.

Download (497kB) | Request a copy

Identification Number: 10.1016/j.jeconom.2023.01.007

Abstract

Many scientic and economic applications involve the statistical learning of high-dimensional functional time series, where the number of functional variables is comparable to, or even greater than, the number of serially dependent functional observations. In this paper, we model observed functional time series, which are subject to errors in the sense that each functional datum arises as the sum of two uncorrelated components, one dynamic and one white noise. Motivated from the fact that the autocovariance function of observed functional time series automatically lters out the noise term, we propose a three-step framework by rst performing autocovariance-based dimension reduction, then formulating a novel autocovariance-based block regularized minimum distance estimation to produce block sparse estimates, and based on which obtaining the nal functional sparse estimates. We investigate theoretical properties of the proposed estimators, and illustrate the proposed estimation procedure with the corresponding convergence analysis via three sparse high-dimensional functional time series models. We demonstrate via both simulated and real datasets that our proposed estimators signicantly outperform their competitors.

Item Type: Article
Additional Information: © 2023 The Author(s).
Divisions: Statistics
Subjects: H Social Sciences > HA Statistics
JEL classification: C - Mathematical and Quantitative Methods > C1 - Econometric and Statistical Methods: General > C13 - Estimation
C - Mathematical and Quantitative Methods > C3 - Econometric Methods: Multiple; Simultaneous Equation Models; Multiple Variables; Endogenous Regressors > C32 - Time-Series Models
C - Mathematical and Quantitative Methods > C5 - Econometric Modeling > C50 - General
Date Deposited: 17 Jan 2023 09:54
Last Modified: 12 Mar 2023 19:03
URI: http://eprints.lse.ac.uk/id/eprint/117910

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics