Department of Economics and Business Economics

Estimation and Forecasting in Vector Autoregressive Moving Average Models for Rich Datasets

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Standard

Estimation and Forecasting in Vector Autoregressive Moving Average Models for Rich Datasets. / Dias, Gustavo Fruet; Kapetanios, George.

In: Journal of Econometrics, Vol. 202, No. 1, 01.01.2018, p. 75-91.

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Harvard

APA

CBE

MLA

Vancouver

Author

Dias, Gustavo Fruet ; Kapetanios, George. / Estimation and Forecasting in Vector Autoregressive Moving Average Models for Rich Datasets. In: Journal of Econometrics. 2018 ; Vol. 202, No. 1. pp. 75-91.

Bibtex

@article{38c5434a743d440c8e3425c191159dc7,
title = "Estimation and Forecasting in Vector Autoregressive Moving Average Models for Rich Datasets",
abstract = "We address the issue of modelling and forecasting macroeconomic variables using rich datasets by adopting the class of Vector Autoregressive Moving Average (VARMA) models. We overcome the estimation issue that arises with this class of models by implementing an iterative ordinary least squares (IOLS) estimator. We establish the consistency and asymptotic distribution of the estimator for weak and strong VARMA(p,q) models. Monte Carlo results show that IOLS is consistent and feasible for large systems, outperforming the MLE and other linear regression based efficient estimators under alternative scenarios. Our empirical application shows that VARMA models are feasible alternatives when forecasting with many predictors. We show that VARMA models outperform the AR(1), ARMA(1,1), Bayesian VAR, and factor models, considering different model dimensions.",
keywords = "ARMA MODELS, Asymptotic contraction mapping, ECHELON-FORM, Forecasting, IDENTIFICATION, Iterative ordinary least squares (IOLS) estimator, LARGE NUMBER, LEAST-SQUARES, MONETARY-POLICY, PRINCIPAL COMPONENTS, RECURSIVE ESTIMATION, REPRESENTATIONS, Rich and large datasets, VARMA, VARMA MODELS, Weak VARMA",
author = "Dias, {Gustavo Fruet} and George Kapetanios",
year = "2018",
month = jan,
day = "1",
doi = "10.1016/j.jeconom.2017.06.022",
language = "English",
volume = "202",
pages = "75--91",
journal = "Journal of Econometrics",
issn = "0304-4076",
publisher = "Elsevier BV",
number = "1",

}

RIS

TY - JOUR

T1 - Estimation and Forecasting in Vector Autoregressive Moving Average Models for Rich Datasets

AU - Dias, Gustavo Fruet

AU - Kapetanios, George

PY - 2018/1/1

Y1 - 2018/1/1

N2 - We address the issue of modelling and forecasting macroeconomic variables using rich datasets by adopting the class of Vector Autoregressive Moving Average (VARMA) models. We overcome the estimation issue that arises with this class of models by implementing an iterative ordinary least squares (IOLS) estimator. We establish the consistency and asymptotic distribution of the estimator for weak and strong VARMA(p,q) models. Monte Carlo results show that IOLS is consistent and feasible for large systems, outperforming the MLE and other linear regression based efficient estimators under alternative scenarios. Our empirical application shows that VARMA models are feasible alternatives when forecasting with many predictors. We show that VARMA models outperform the AR(1), ARMA(1,1), Bayesian VAR, and factor models, considering different model dimensions.

AB - We address the issue of modelling and forecasting macroeconomic variables using rich datasets by adopting the class of Vector Autoregressive Moving Average (VARMA) models. We overcome the estimation issue that arises with this class of models by implementing an iterative ordinary least squares (IOLS) estimator. We establish the consistency and asymptotic distribution of the estimator for weak and strong VARMA(p,q) models. Monte Carlo results show that IOLS is consistent and feasible for large systems, outperforming the MLE and other linear regression based efficient estimators under alternative scenarios. Our empirical application shows that VARMA models are feasible alternatives when forecasting with many predictors. We show that VARMA models outperform the AR(1), ARMA(1,1), Bayesian VAR, and factor models, considering different model dimensions.

KW - ARMA MODELS

KW - Asymptotic contraction mapping

KW - ECHELON-FORM

KW - Forecasting

KW - IDENTIFICATION

KW - Iterative ordinary least squares (IOLS) estimator

KW - LARGE NUMBER

KW - LEAST-SQUARES

KW - MONETARY-POLICY

KW - PRINCIPAL COMPONENTS

KW - RECURSIVE ESTIMATION

KW - REPRESENTATIONS

KW - Rich and large datasets

KW - VARMA

KW - VARMA MODELS

KW - Weak VARMA

UR - http://www.scopus.com/inward/record.url?scp=85029221850&partnerID=8YFLogxK

U2 - 10.1016/j.jeconom.2017.06.022

DO - 10.1016/j.jeconom.2017.06.022

M3 - Journal article

VL - 202

SP - 75

EP - 91

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

IS - 1

ER -