Evaluating the Empirical Performance of Alternative Econometric Models for Oil Price Forecasting

Matteo Manera, Chiara Longo, Anil Markandya, Elisa Scarpa

Research output: Working paper

Abstract

The relevance of oil in the world economy explains why considerable effort has been devoted to the development of different types of econometric models for oil price forecasting. Several specifications have been proposed in the economic literature. Some are based on financial theory and concentrate on the relationship between spot and futures prices ("financial" models). Others assign a key role to variables explaining the characteristics of the physical oil market ("structural" models). The empirical literature is very far from any consensus about the appropriate model for oil price forecasting that should be implemented. Relative to the previous literature, this paper is novel in several respects. First of all, we test and systematically evaluate the ability of several alternative econometric specifications proposed in the literature to capture the dynamics of oil prices. Second, we analyse the effects of different data frequencies on the coefficient estimates and forecasts obtained using each selected econometric specification. Third, we compare different models at different data frequencies on a common sample and common data. Fourth, we evaluate the forecasting performance of each selected model using static and dynamic forecasts, as well as different measures of forecast errors. Finally, we propose a new class of models which combine the relevant aspects of the financial and structural specifications proposed in the literature ("mixed" models). Our empirical findings can be summarized as follows. Financial models in levels do not produce satisfactory forecasts for the WTI spot price. The financial error correction model yields accurate in-sample forecasts. Real and strategic variables alone are insufficient to capture the oil spot price dynamics in the forecasting sample. Our proposed mixed models are statistically adequate and exhibit accurate forecasts. Different data frequencies seem to affect the forecasting ability of the models under analysis.
Original languageEnglish
PublisherFondazione Eni Enrico Mattei
Publication statusPublished - 2007

Fingerprint

Econometric models
Oil prices
Price forecasting
Spot price
Mixed model
Oil
Financial models
Econometrics
Error correction model
Structural model
Forecasting performance
Economics
Forecast error
World economy
Futures prices
Price dynamics
Oil markets
Coefficients

Keywords

  • Energy and the Macroeconomy
  • Model Evaluation and Selection
  • Forecasting and Other Model Applications
  • Exhaustible Resources and Economic Development

Cite this

Manera, M., Longo, C., Markandya, A., & Scarpa, E. (2007). Evaluating the Empirical Performance of Alternative Econometric Models for Oil Price Forecasting. Fondazione Eni Enrico Mattei.

Evaluating the Empirical Performance of Alternative Econometric Models for Oil Price Forecasting. / Manera, Matteo; Longo, Chiara; Markandya, Anil; Scarpa, Elisa.

Fondazione Eni Enrico Mattei, 2007.

Research output: Working paper

Manera, M, Longo, C, Markandya, A & Scarpa, E 2007 'Evaluating the Empirical Performance of Alternative Econometric Models for Oil Price Forecasting' Fondazione Eni Enrico Mattei.
Manera M, Longo C, Markandya A, Scarpa E. Evaluating the Empirical Performance of Alternative Econometric Models for Oil Price Forecasting. Fondazione Eni Enrico Mattei. 2007.
Manera, Matteo ; Longo, Chiara ; Markandya, Anil ; Scarpa, Elisa. / Evaluating the Empirical Performance of Alternative Econometric Models for Oil Price Forecasting. Fondazione Eni Enrico Mattei, 2007.
@techreport{7c8d8ad22ce544a182a7ac759db11040,
title = "Evaluating the Empirical Performance of Alternative Econometric Models for Oil Price Forecasting",
abstract = "The relevance of oil in the world economy explains why considerable effort has been devoted to the development of different types of econometric models for oil price forecasting. Several specifications have been proposed in the economic literature. Some are based on financial theory and concentrate on the relationship between spot and futures prices ({"}financial{"} models). Others assign a key role to variables explaining the characteristics of the physical oil market ({"}structural{"} models). The empirical literature is very far from any consensus about the appropriate model for oil price forecasting that should be implemented. Relative to the previous literature, this paper is novel in several respects. First of all, we test and systematically evaluate the ability of several alternative econometric specifications proposed in the literature to capture the dynamics of oil prices. Second, we analyse the effects of different data frequencies on the coefficient estimates and forecasts obtained using each selected econometric specification. Third, we compare different models at different data frequencies on a common sample and common data. Fourth, we evaluate the forecasting performance of each selected model using static and dynamic forecasts, as well as different measures of forecast errors. Finally, we propose a new class of models which combine the relevant aspects of the financial and structural specifications proposed in the literature ({"}mixed{"} models). Our empirical findings can be summarized as follows. Financial models in levels do not produce satisfactory forecasts for the WTI spot price. The financial error correction model yields accurate in-sample forecasts. Real and strategic variables alone are insufficient to capture the oil spot price dynamics in the forecasting sample. Our proposed mixed models are statistically adequate and exhibit accurate forecasts. Different data frequencies seem to affect the forecasting ability of the models under analysis.",
keywords = "Energy and the Macroeconomy, Model Evaluation and Selection, Forecasting and Other Model Applications, Exhaustible Resources and Economic Development",
author = "Matteo Manera and Chiara Longo and Anil Markandya and Elisa Scarpa",
note = "ID number: No. 2007.4",
year = "2007",
language = "English",
publisher = "Fondazione Eni Enrico Mattei",
type = "WorkingPaper",
institution = "Fondazione Eni Enrico Mattei",

}

TY - UNPB

T1 - Evaluating the Empirical Performance of Alternative Econometric Models for Oil Price Forecasting

AU - Manera, Matteo

AU - Longo, Chiara

AU - Markandya, Anil

AU - Scarpa, Elisa

N1 - ID number: No. 2007.4

PY - 2007

Y1 - 2007

N2 - The relevance of oil in the world economy explains why considerable effort has been devoted to the development of different types of econometric models for oil price forecasting. Several specifications have been proposed in the economic literature. Some are based on financial theory and concentrate on the relationship between spot and futures prices ("financial" models). Others assign a key role to variables explaining the characteristics of the physical oil market ("structural" models). The empirical literature is very far from any consensus about the appropriate model for oil price forecasting that should be implemented. Relative to the previous literature, this paper is novel in several respects. First of all, we test and systematically evaluate the ability of several alternative econometric specifications proposed in the literature to capture the dynamics of oil prices. Second, we analyse the effects of different data frequencies on the coefficient estimates and forecasts obtained using each selected econometric specification. Third, we compare different models at different data frequencies on a common sample and common data. Fourth, we evaluate the forecasting performance of each selected model using static and dynamic forecasts, as well as different measures of forecast errors. Finally, we propose a new class of models which combine the relevant aspects of the financial and structural specifications proposed in the literature ("mixed" models). Our empirical findings can be summarized as follows. Financial models in levels do not produce satisfactory forecasts for the WTI spot price. The financial error correction model yields accurate in-sample forecasts. Real and strategic variables alone are insufficient to capture the oil spot price dynamics in the forecasting sample. Our proposed mixed models are statistically adequate and exhibit accurate forecasts. Different data frequencies seem to affect the forecasting ability of the models under analysis.

AB - The relevance of oil in the world economy explains why considerable effort has been devoted to the development of different types of econometric models for oil price forecasting. Several specifications have been proposed in the economic literature. Some are based on financial theory and concentrate on the relationship between spot and futures prices ("financial" models). Others assign a key role to variables explaining the characteristics of the physical oil market ("structural" models). The empirical literature is very far from any consensus about the appropriate model for oil price forecasting that should be implemented. Relative to the previous literature, this paper is novel in several respects. First of all, we test and systematically evaluate the ability of several alternative econometric specifications proposed in the literature to capture the dynamics of oil prices. Second, we analyse the effects of different data frequencies on the coefficient estimates and forecasts obtained using each selected econometric specification. Third, we compare different models at different data frequencies on a common sample and common data. Fourth, we evaluate the forecasting performance of each selected model using static and dynamic forecasts, as well as different measures of forecast errors. Finally, we propose a new class of models which combine the relevant aspects of the financial and structural specifications proposed in the literature ("mixed" models). Our empirical findings can be summarized as follows. Financial models in levels do not produce satisfactory forecasts for the WTI spot price. The financial error correction model yields accurate in-sample forecasts. Real and strategic variables alone are insufficient to capture the oil spot price dynamics in the forecasting sample. Our proposed mixed models are statistically adequate and exhibit accurate forecasts. Different data frequencies seem to affect the forecasting ability of the models under analysis.

KW - Energy and the Macroeconomy

KW - Model Evaluation and Selection

KW - Forecasting and Other Model Applications

KW - Exhaustible Resources and Economic Development

UR - http://www.feem.it/NR/rdonlyres/9635614F-C1B7-4A58-AC9E-1DE4F271E774/2228/409.pdf

M3 - Working paper

BT - Evaluating the Empirical Performance of Alternative Econometric Models for Oil Price Forecasting

PB - Fondazione Eni Enrico Mattei

ER -