Time series forecasting with the WARIMAX-GARCH method

Abstract

Time series forecasting with the WARIMAX-GARCH method, Neurocomputing, http://dx.doi.org/10. 1016/j.neucom.2016.08.046 This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting galley proof before it is published in its final citable form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain. AbstractIt is well-known that causal forecasting methods that include appropriately chosen Exogenous Variables (EVs) very often present improved forecasting performances over univariate methods. However, in practice, EVs are usually difficult to obtain and in many cases are not available at all. In this paper, a new causal forecasting approach, called Wavelet Auto-Regressive Integrated Moving Average with eXogenous variables and Generalized Auto-Regressive Conditional Heteroscedasticity (WARIMAX-GARCH) method, is proposed to improve predictive performance and accuracy but also to address, at least in part, the problem of unavailable EVs. Basically, the WARIMAX-GARCH method obtains Wavelet "EVs" (WEVs) from Auto-Regressive Integrated Moving Average with eXogenous variables and Generalized Auto-Regressive Conditional Heteroscedasticity (ARIMAX-GARCH) models applied to Wavelet Components (WCs) that are initially determined from the underlying time series. The WEVs are, in fact, treated by the WARIMAX-GARCH method as if they were conventional EVs. Similarly to GARCH and ARIMA-GARCH models, the WARIMAX-GARCH method is suitable for time series exhibiting non-linear characteristics such as conditional variance that depends on past values of observed data. However, unlike those, it can explicitly model frequency domain patterns in the series to help improve predictive performance. An application to a daily time series of dam displacement in Brazil shows the WARIMAX-GARCH method to remarkably outperform the ARIMA-GARCH method, as well as the (multi-layer perceptron) Artificial Neural Network (ANN) and its wavelet version referred to as Wavelet Artificial Neural Network (WANN) as in [1], on statistical measures for both in-sample and out-of-sample forecasting.

Modelling of trends in the volume and structure of accumulated credit indebtedness in the banking system

“…Недостатком таких моделей является то, что они могут улавливать несущественную или зашумленную информацию как основу для прогнозирования. В работах [Zhang, Frey, 2015;Corrêa et al, 2016] показано, что такие модели могут давать довольно точные прогнозы и достаточно просты в реализации.…”

Understanding volatility and leverage effects in bunker markets

“…The model used is a bivariate exponential GARCH (EGARCH-M) in the mean model in which we incorporate economic uncertainty, real oil price and real exchange rate in addition to energy consumption and real GDP. In addition to this, studies like Corra (2016) used Wavelet Auto-Regressive Integrated Moving Average with exogenous variables and Generalised Auto-Regressive Conditional heteroskedasticity (WARIMAX-GARCH) and ARIMA-GARCH method. While researchers like Vortelinos (2015) used HAR (Heterogeneous Auto-Regressive Model); Principal Components Combining; Neural networks; GARCH; Volatility studies in the study.…”

Previsão de Deslocamentos Verticais Medido por Extensômetros de um Bloco da Barragem da Usina Hidrelétrica de Itaipu

“…Pesquisadores buscam constantemente estudar e desenvolver modelos estatísticos confiáveis e que apresentem boa precisão e, neste contexto muitos métodos híbridos são apresentados, como pode ser visto em: (HICKMANN et al, 2016), (CORRÊA et al, 2016), , (WALLIS, 2011), (MORETTIN;TOLOI, 2006) e (DE GOOIJER; HYNDMAN, 2006). Estes ressaltam que independentemente da metodologia utilizada na previsão o objetivo é minimizar erros provenientes dos processos utilizados na obtenção de previsões (BOX; JENKINS; REINSEL, 2008b).…”