Optimal real-time filters for linear prediction problems

Wildi, Marc; McElroy, Tucker

doi:10.21256/zhaw-4906

Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-4906

Publication type:	Article in scientific journal
Type of review:	Peer review (publication)
Title:	Optimal real-time filters for linear prediction problems
Authors:	Wildi, Marc McElroy, Tucker
DOI:	10.21256/zhaw-4906 10.1515/jtse-2014-0019
Published in:	Journal of Time Series Econometrics
Volume(Issue):	8
Issue:	2
Page(s):	155
Pages to:	192
Issue Date:	2016
Publisher / Ed. Institution:	De Gruyter
ISSN:	2194-6507 1941-1928
Language:	English
Subject (DDC):	003: Systems
Abstract:	The classic model-based paradigm in time series analysis is rooted in the Wold decomposition of the data-generating process into an uncorrelated white noise process. By design, this universal decomposition is indifferent to particular features of a specific prediction problem (e. g., forecasting or signal extraction) – or features driven by the priorities of the data-users. A single optimization principle (one-step ahead forecast error minimization) is proposed by this classical paradigm to address a plethora of prediction problems. In contrast, this paper proposes to reconcile prediction problem structures, user priorities, and optimization principles into a general framework whose scope encompasses the classic approach. We introduce the linear prediction problem (LPP), which in turn yields an LPP objective function. Then one can fit models via LPP minimization, or one can directly optimize the linear filter corresponding to the LPP, yielding the Direct Filter Approach. We provide theoretical results and practical algorithms for both applications of the LPP, and discuss the merits and limitations of each. Our empirical illustrations focus on trend estimation (low-pass filtering) and seasonal adjustment in real-time, i. e., constructing filters that depend only on present and past data.
Further description:	Erworben im Rahmen der Schweizer Nationallizenzen (http://www.nationallizenzen.ch)
URI:	https://digitalcollection.zhaw.ch/handle/11475/13385
Fulltext version:	Published version
License (according to publishing contract):	Licence according to publishing contract
Departement:	School of Engineering
Organisational Unit:	Institute of Data Analysis and Process Design (IDP)
Appears in collections:	Publikationen School of Engineering

Files in This Item:

File	Description	Size	Format
2016_Wildi-McElroy_Real-time-filters-linear-prediction-problems.pdf	Version of Record	2.61 MB	Adobe PDF	View/Open
2016_Wildi_Optimal_real_time_filters_for_linear_prediction_problems.pdf	Accepted Version	545.29 kB	Adobe PDF	View/Open

Show full item record

Wildi, M., & McElroy, T. (2016). Optimal real-time filters for linear prediction problems. Journal of Time Series Econometrics, 8(2), 155–192. https://doi.org/10.21256/zhaw-4906

Wildi, M. and McElroy, T. (2016) ‘Optimal real-time filters for linear prediction problems’, Journal of Time Series Econometrics, 8(2), pp. 155–192. Available at: https://doi.org/10.21256/zhaw-4906.

M. Wildi and T. McElroy, “Optimal real-time filters for linear prediction problems,” Journal of Time Series Econometrics, vol. 8, no. 2, pp. 155–192, 2016, doi: 10.21256/zhaw-4906.

WILDI, Marc und Tucker MCELROY, 2016. Optimal real-time filters for linear prediction problems. Journal of Time Series Econometrics. 2016. Bd. 8, Nr. 2, S. 155–192. DOI 10.21256/zhaw-4906

Wildi, Marc, and Tucker McElroy. 2016. “Optimal Real-Time Filters for Linear Prediction Problems.” Journal of Time Series Econometrics 8 (2): 155–92. https://doi.org/10.21256/zhaw-4906.

Wildi, Marc, and Tucker McElroy. “Optimal Real-Time Filters for Linear Prediction Problems.” Journal of Time Series Econometrics, vol. 8, no. 2, 2016, pp. 155–92, https://doi.org/10.21256/zhaw-4906.