Long-term forecasting of El Niño events via dynamic factor simulations

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

Standard

Long-term forecasting of El Niño events via dynamic factor simulations. / Li, Mengheng; Koopman, Siem Jan; Lit, Rutger; Petrova, Desislava.

In: Journal of Econometrics, Vol. 214, No. 1, 01.2020, p. 46-66.

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

Harvard

Li, M, Koopman, SJ, Lit, R & Petrova, D 2020, 'Long-term forecasting of El Niño events via dynamic factor simulations', Journal of Econometrics, vol. 214, no. 1, pp. 46-66. https://doi.org/10.1016/j.jeconom.2019.05.004

APA

CBE

MLA

Vancouver

Author

Li, Mengheng ; Koopman, Siem Jan ; Lit, Rutger ; Petrova, Desislava. / Long-term forecasting of El Niño events via dynamic factor simulations. In: Journal of Econometrics. 2020 ; Vol. 214, No. 1. pp. 46-66.

Bibtex

@article{efc2dfbdb78247b4a7dad83a611492e4,
title = "Long-term forecasting of El Ni{\~n}o events via dynamic factor simulations",
abstract = "We propose a new forecasting procedure which particularly explores opportunities for improving the precision of medium and long-term forecasts of the Ni{\~n}o3.4 time series that is linked with the well-known El Ni{\~n}o phenomenon. This important climatic time series is subject to an intricate dynamic structure and is interrelated to other climatological variables. The procedure consists of three steps. First, a univariate time series model is considered for producing prediction errors. Second, signal paths of the prediction errors are simulated via a dynamic factor model for the errors and explanatory variables. From these simulated errors, ensemble time series for Ni{\~n}o3.4 are constructed. Third, forecasts are generated from the ensemble time series and their sample average is our final forecast. As part of these dynamic factor simulations, we also obtain the forecast of the El Ni{\~n}o event which is a categorical variable. We present empirical evidence that our procedure can be superior in its forecasting performance when compared to other econometric forecasting methods.",
keywords = "Climate econometrics, Dynamic models, Factor models, Kalman filter, Long-term forecast, Multivariate time series, Simulation smoothing, Unobserved components, TESTS, ENSO, SEA-SURFACE TEMPERATURES, COMPONENTS, PREDICTION, PREDICTABILITY, MODELS, LIKELIHOOD",
author = "Mengheng Li and Koopman, {Siem Jan} and Rutger Lit and Desislava Petrova",
year = "2020",
month = jan,
doi = "10.1016/j.jeconom.2019.05.004",
language = "English",
volume = "214",
pages = "46--66",
journal = "Journal of Econometrics",
issn = "0304-4076",
publisher = "Elsevier BV",
number = "1",

}

RIS

TY - JOUR

T1 - Long-term forecasting of El Niño events via dynamic factor simulations

AU - Li, Mengheng

AU - Koopman, Siem Jan

AU - Lit, Rutger

AU - Petrova, Desislava

PY - 2020/1

Y1 - 2020/1

N2 - We propose a new forecasting procedure which particularly explores opportunities for improving the precision of medium and long-term forecasts of the Niño3.4 time series that is linked with the well-known El Niño phenomenon. This important climatic time series is subject to an intricate dynamic structure and is interrelated to other climatological variables. The procedure consists of three steps. First, a univariate time series model is considered for producing prediction errors. Second, signal paths of the prediction errors are simulated via a dynamic factor model for the errors and explanatory variables. From these simulated errors, ensemble time series for Niño3.4 are constructed. Third, forecasts are generated from the ensemble time series and their sample average is our final forecast. As part of these dynamic factor simulations, we also obtain the forecast of the El Niño event which is a categorical variable. We present empirical evidence that our procedure can be superior in its forecasting performance when compared to other econometric forecasting methods.

AB - We propose a new forecasting procedure which particularly explores opportunities for improving the precision of medium and long-term forecasts of the Niño3.4 time series that is linked with the well-known El Niño phenomenon. This important climatic time series is subject to an intricate dynamic structure and is interrelated to other climatological variables. The procedure consists of three steps. First, a univariate time series model is considered for producing prediction errors. Second, signal paths of the prediction errors are simulated via a dynamic factor model for the errors and explanatory variables. From these simulated errors, ensemble time series for Niño3.4 are constructed. Third, forecasts are generated from the ensemble time series and their sample average is our final forecast. As part of these dynamic factor simulations, we also obtain the forecast of the El Niño event which is a categorical variable. We present empirical evidence that our procedure can be superior in its forecasting performance when compared to other econometric forecasting methods.

KW - Climate econometrics

KW - Dynamic models

KW - Factor models

KW - Kalman filter

KW - Long-term forecast

KW - Multivariate time series

KW - Simulation smoothing

KW - Unobserved components

KW - TESTS

KW - ENSO

KW - SEA-SURFACE TEMPERATURES

KW - COMPONENTS

KW - PREDICTION

KW - PREDICTABILITY

KW - MODELS

KW - LIKELIHOOD

UR - http://www.scopus.com/inward/record.url?scp=85069903803&partnerID=8YFLogxK

U2 - 10.1016/j.jeconom.2019.05.004

DO - 10.1016/j.jeconom.2019.05.004

M3 - Journal article

AN - SCOPUS:85069903803

VL - 214

SP - 46

EP - 66

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

IS - 1

ER -