WHAT CENTRAL BANKERS NEED TO KNOW ABOUT FORECASTING OIL PRICES

• 成果类型: Article
• 署名作者: Baumeister, Christiane; Kilian, Lutz
• 署名单位: University of Michigan System; University of Michigan
• 刊物名称: INTERNATIONAL ECONOMIC REVIEW
• ISSN/ISSBN: 0020-6598
• DOI: 10.1111/iere.12074
• 发表日期: 2014
• 页码: 869-889
• 关键词: real; uncertainty; inflation; output

摘要

Central banks routinely use short-horizon forecasts of the quarterly price of oil in assessing the global and domestic economic outlook. We address a number of econometric issues specific to the construction of quarterly oil price forecasts in the United States and abroad. We show that quarterly forecasts of the real price of oil from suitably designed vector autoregressive models estimated on monthly data generate the most accurate real-time forecasts overall among a wide range of methods, including quarterly averages of forecasts based on monthly oil futures prices, no-change forecasts, and forecasts based on regression models estimated on quarterly data.