Estimation in Functional Lagged Regression

Siegfried Hörmann, Lukasz Kidzinski, Piotr P. Kokoszka

Research output: Contribution to journalArticle

Abstract

The paper introduces a functional time series (lagged) regression model. The impulse-response coefficients in such a model are operators acting on a separable Hilbert space, which is the function space L2 in applications. A spectral approach to the estimation of these coefficients is proposed and asymptotically justified under a general nonparametric condition on the temporal dependence of the input series. Since the data are infinite-dimensional, the estimation involves a spectral-domain dimension-reduction technique. Consistency of the estimators is established under general data-dependent assumptions on the rate of the dimension-reduction parameter. Their finite-sample performance is evaluated by a simulation study that compares two ad hoc approaches to dimension reduction with an alternative, asymptotically justified method.
LanguageUndefined/Unknown
Pages541-561
Number of pages21
JournalJournal of time series analysis
Volume36
Issue number4
StatusPublished - 2015

Cite this

Hörmann, S., Kidzinski, L., & Kokoszka, P. P. (2015). Estimation in Functional Lagged Regression. Journal of time series analysis, 36(4), 541-561.

Estimation in Functional Lagged Regression. / Hörmann, Siegfried; Kidzinski, Lukasz; Kokoszka, Piotr P.

In: Journal of time series analysis, Vol. 36, No. 4, 2015, p. 541-561.

Research output: Contribution to journalArticle

Hörmann, S, Kidzinski, L & Kokoszka, PP 2015, 'Estimation in Functional Lagged Regression' Journal of time series analysis, vol 36, no. 4, pp. 541-561.
Hörmann, Siegfried ; Kidzinski, Lukasz ; Kokoszka, Piotr P./ Estimation in Functional Lagged Regression. In: Journal of time series analysis. 2015 ; Vol. 36, No. 4. pp. 541-561
@article{79e9047197f74ae39f0473c235a227ca,
title = "Estimation in Functional Lagged Regression",
abstract = "The paper introduces a functional time series (lagged) regression model. The impulse-response coefficients in such a model are operators acting on a separable Hilbert space, which is the function space L2 in applications. A spectral approach to the estimation of these coefficients is proposed and asymptotically justified under a general nonparametric condition on the temporal dependence of the input series. Since the data are infinite-dimensional, the estimation involves a spectral-domain dimension-reduction technique. Consistency of the estimators is established under general data-dependent assumptions on the rate of the dimension-reduction parameter. Their finite-sample performance is evaluated by a simulation study that compares two ad hoc approaches to dimension reduction with an alternative, asymptotically justified method.",
author = "Siegfried H{\"o}rmann and Lukasz Kidzinski and Kokoszka, {Piotr P.}",
note = "DOI: 10.1111/jtsa.12114",
year = "2015",
language = "undefiniert/unbekannt",
volume = "36",
pages = "541--561",
journal = "Journal of time series analysis",
issn = "0143-9782",
publisher = "Wiley-Blackwell",
number = "4",

}

TY - JOUR

T1 - Estimation in Functional Lagged Regression

AU - Hörmann,Siegfried

AU - Kidzinski,Lukasz

AU - Kokoszka,Piotr P.

N1 - DOI: 10.1111/jtsa.12114

PY - 2015

Y1 - 2015

N2 - The paper introduces a functional time series (lagged) regression model. The impulse-response coefficients in such a model are operators acting on a separable Hilbert space, which is the function space L2 in applications. A spectral approach to the estimation of these coefficients is proposed and asymptotically justified under a general nonparametric condition on the temporal dependence of the input series. Since the data are infinite-dimensional, the estimation involves a spectral-domain dimension-reduction technique. Consistency of the estimators is established under general data-dependent assumptions on the rate of the dimension-reduction parameter. Their finite-sample performance is evaluated by a simulation study that compares two ad hoc approaches to dimension reduction with an alternative, asymptotically justified method.

AB - The paper introduces a functional time series (lagged) regression model. The impulse-response coefficients in such a model are operators acting on a separable Hilbert space, which is the function space L2 in applications. A spectral approach to the estimation of these coefficients is proposed and asymptotically justified under a general nonparametric condition on the temporal dependence of the input series. Since the data are infinite-dimensional, the estimation involves a spectral-domain dimension-reduction technique. Consistency of the estimators is established under general data-dependent assumptions on the rate of the dimension-reduction parameter. Their finite-sample performance is evaluated by a simulation study that compares two ad hoc approaches to dimension reduction with an alternative, asymptotically justified method.

M3 - Artikel

VL - 36

SP - 541

EP - 561

JO - Journal of time series analysis

T2 - Journal of time series analysis

JF - Journal of time series analysis

SN - 0143-9782

IS - 4

ER -