管理评论 ›› 2020, Vol. 32 ›› Issue (7): 29-40.

• 中国系统管理学专辑 • 上一篇    下一篇

不确定性与原油市场的交互影响测度:基于综合集成的多尺度方法论

冯钰瑶1,2, 刘畅1,2, 孙晓蕾1,2   

  1. 1. 中国科学院科技战略咨询研究院, 北京 100190;
    2. 中国科学院大学公共政策与管理学院, 北京 100049
  • 收稿日期:2019-09-16 出版日期:2020-07-28 发布日期:2020-08-08
  • 通讯作者: 孙晓蕾(通讯作者),中国科学院科技战略咨询研究院、中国科学院大学公共政策与管理学院研究员,硕士生导师,博士
  • 作者简介:冯钰瑶,中国科学院科技战略咨询研究院、中国科学院大学公共政策与管理学院博士研究生;刘畅,中国科学院科技战略咨询研究院、中国科学院大学公共政策与管理学院博士研究生。
  • 基金资助:
    国家自然科学基金项目(71771206);国家自然科学基金项目(71425002)。

Measuring the Interaction between Uncertainty and Crude Oil Market: A Multiscale Methodology Based on Synthetic Integration

Feng Yuyao1,2, Liu Chang1,2, Sun Xiaolei1,2   

  1. 1. Institutes of Science and Development, Chinese Academy of Sciences, Beijing 100190;
    2. School of Public policy and Management, University of Chinese Academy of Sciences, Beijing 100049
  • Received:2019-09-16 Online:2020-07-28 Published:2020-08-08

摘要: 能源系统作为一个典型的复杂系统,其发展过程中极易受到多种来自外部环境的不确定性因素的影响。基于复杂系统管理学思想,针对原油的金融属性、商品属性和政治属性,将经济政策不确定性、市场恐慌以及地缘政治风险等不同层面的不确定性因素纳入到同一框架下,构建了基于综合集成的多尺度复杂系统研究方法论,对不确定性与原油市场形成的复杂系统在不同时间、频率及价格水平下的影响规律及作用机理进行研究。研究选取了6个不确定性指标和原油期货价格1997-2019年间共270个月度数据,借助小波分析和分位数回归方法,发现不确定性与原油市场的交互影响在不同指标间、不同时频尺度及不同价格水平下表现各异。这有助于深入了解原油市场与不确定性系统间复杂的交互机制,对利益相关者合理决策具有重要参考价值。

关键词: 不确定性, 油价, 多尺度, 小波分析, 分位数回归

Abstract: As a typical complex system, the energy system is highly susceptible to a variety of uncertainty factors from the external environment during its development. Based on the thought of complex systems management, this paper incorporates different levels of uncertainty, including economic policy uncertainty, market panic and geopolitical risk into the same framework according to the financial attributes, commodity attributes and political attributes of crude oil. And a multi-scale complex system research methodology based on meta-synthesis is constructed to study the influence rule and mechanism of the complex system formed by uncertainties and crude oil market at different time, frequency and price levels. In this paper, six uncertainty indicators and crude oil futures price for a total of 270 months from 1997 to 2019 are selected. With the help of wavelet analysis and quantile regression method, the study finds that the interaction between uncertainties and the crude oil market varies between different indicators, time-frequency scales and different price levels. This helps understand the complex interaction mechanism between the crude oil market and the uncertainty system, and has important reference value for the reasonable decision-making of stakeholders.

Key words: uncertainty, oil price, multi-scale, wavelet analysis, quantile regression