The Principle of Overcompleteness in Multivariate Economic Time Series Models

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14560%2F06%3A00031653" target="_blank" >RIV/00216224:14560/06:00031653 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

The Principle of Overcompleteness in Multivariate Economic Time Series Models

Popis výsledku v původním jazyce

In this paper we apply the principle of overcompleteness to sparse parameter estimation in multivariate ARMA models (VARMA models). This new approach is based on the Basis Pursuit Algorithm originally suggested by Chen et al [1]. Overcompleteness means that we admit higher range of orders within which we are looking for lowest possible number of significant parameters (sparsity). A previous study confirmed that this relaxation of the commonly used low-order assumption may yield more precise forecasts from ARMA models when compared with standard statistical estimation techniques. Here an analogical approach will be used for the analysis of multivariate economic time series. It is well-known that particular time series are strongly cross-correlated. Thatis why we expect our technique to be possibly successful for the multivariate case too.

Název v anglickém jazyce

The Principle of Overcompleteness in Multivariate Economic Time Series Models

Popis výsledku anglicky

In this paper we apply the principle of overcompleteness to sparse parameter estimation in multivariate ARMA models (VARMA models). This new approach is based on the Basis Pursuit Algorithm originally suggested by Chen et al [1]. Overcompleteness means that we admit higher range of orders within which we are looking for lowest possible number of significant parameters (sparsity). A previous study confirmed that this relaxation of the commonly used low-order assumption may yield more precise forecasts from ARMA models when compared with standard statistical estimation techniques. Here an analogical approach will be used for the analysis of multivariate economic time series. It is well-known that particular time series are strongly cross-correlated. Thatis why we expect our technique to be possibly successful for the multivariate case too.

Druh

D - Stať ve sborníku

CEP obor

AH - Ekonomie

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2006

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Mathematical Methods in Economics 2006

ISBN

80-7043-479-1

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

—

Název nakladatele

University of Pilsen

Místo vydání

Plzeň

Místo konání akce

Plzeň

Datum konání akce

1. 1. 2006

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000262064700057