Are there gains from pooling real-time oil price forecasts?

Abstract

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. iii Terms of use: Documents in AbstractThe answer as to whether there are gains from pooling real-time oil price forecasts depends on the objective. The approach of combining five of the leading forecasting models with equal weights dominates the strategy of selecting one model and using it for all horizons up to two years. Even more accurate forecasts, however, are obtained when allowing the forecast combinations to vary across forecast horizons. While the latter approach is not always more accurate than selecting the single most accurate forecasting model by horizon, its accuracy can be shown to be much more stable over time. The mean-squared prediction error of real-time pooled forecasts is between 3% and 29% lower than that of the no-change forecast and its directional accuracy as high as 73%. Our results are robust to alternative oil price measures and apply to monthly as well as quarterly forecasts. We illustrate how forecast pooling may be used to produce real-time forecasts of the real and the nominal price of oil in a format consistent with that employed by the U.S. Energy Information Administration in releasing its short-term oil price forecasts, and we compare these forecasts during key historical episodes. JEL classification: Q43, C53 Bank classification: Econometric and statistical methods; International topics RésuméLa combinaison de modèles de prévision en temps réel du prix du pétrole présente-t-elle des avantages? La réponse dépend de l'objectif. La méthode consistant à mettre en commun cinq des principaux modèles de prévision en leur attribuant un poids uniforme prime sur la stratégie visant à choisir un seul modèle et à l'utiliser à des horizons allant jusqu'à deux ans. Il est même possible d'accroître la justesse des prévisions en faisant varier les combinaisons de modèles selon les horizons. Bien que cette approche ne produise pas systématiquement des prévisions plus exactes que celles obtenues en sélectionnant le modèle qui offre la meilleure qualité prédictive à chaque horizon, la précision des projections fournies se révèle beaucoup plus stable au fil du temps. En effet, les prévisions en temps réel réunies présentent une erreur quadratique moyenne de 3 % à 29 % inférieure à celle d'une marche aléatoire et indiquent avec exactitude le sens des variations dans 73 % des cas. Ces résultats ne dépendent pas de la mesure du prix du pétrole retenue et s'appliquent tant aux prévisions mensuelles qu'aux prévisions trimestrielles. Les auteu...

Real‐time forecast combinations for the oil price

“…The next section summarizes the real-time oil market data set, together with the forecast combination methods deployed by Baumeister and Kilian (2015), also considered by Baumeister, Kilian, and Lee (2014). The next section summarizes the real-time oil market data set, together with the forecast combination methods deployed by Baumeister and Kilian (2015), also considered by Baumeister, Kilian, and Lee (2014).…”

Inside the Crystal Ball: New Approaches to Predicting the Gasoline Price at the Pump

“…We rely on data from a suitably updated real‐time database developed in Baumeister and Kilian (, ) and extended in Baumeister et al (,). The reader is referred to these references for a detailed description of the data sources and definitions.…”

Improving the Forecasting Accuracy of Crude Oil Prices

“…We consider the West Texas Intermediate crude oil prices (WTI) as a proxy for crude oil. Recently, Alquist and Kilian (2010) [15], Alquist et al (2013) [18], Baumeister et al (2013Baumeister et al ( , 2014Baumeister et al ( , 2015 [13,17,19], [12], Xiong et al (2013) [20], Yin and Yang (2016) [21], Drachal (2016) [10] and Naser (2016) [11] all regarded WTI as a proxy variable for oil prices. We selected four factors: supply, demand, crack spread, and non-energy commodity prices.…”

“…According to economic theory, supply and demand are the key factors for changing the price of a commodity. Therefore, many researchers employ it as an independent variable to forecast oil prices (Baumeister and Kilian (2012) [22], Fattouh et al (2013) [23], Hamilton (2009) [4], [12], Baumeister et al (2013Baumeister et al ( , 2014Baumeister et al ( , 2015 [13,17,19]), and we follow in their steps. For supply, two factors-oil production and oil inventory-were selected.…”