Uncovering Long-Run Economic Relationships in High-Frequency Financial Data -- An Accomplishment Based Renewal

揭示高频金融数据中的长期经济关系——基于成就的更新

• 批准号: 0111802
• 负责人: Tim Bollerslev
• 金额: $ 16.78万
• 依托单位: National Bureau of Economic Research Inc
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2001
• 资助国家: 美国
• 起止时间: 2001-09-01 至 2006-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0111802&HistoricalAwards=false
• 关键词: Uncovering; Long; Run; Economic; Relationships

The advent of computerized communication networks and automated trade execution systems have resulted in the recent availability of real-time prices and information variables for a host of different financial markets and instruments. This project aims to expand on the ability to extract useful information about important economic phenomena from this new rich source of data. Specifically, the high-frequency data hold the promise of delivering: (i) a much better understanding of the type of information that induces important price movements and their relation to the underlying market microstructure; (ii) a deeper understanding concerning the functioning of markets and the effectiveness of various macroeconomic policies; (iii) the development of new and more accurate risk measurements; and (iv) important information about the longer-run interday volatility dependencies that play a crucial role in asset pricing and risk management. Meanwhile, it has become increasingly clear that the satisfactory empirical analysis of high -frequency data presents a host of unique and challenging problems, requiring the development of new modeling paradigms and specialized procedures relative to the techniques employed in traditional time series econometrics involving the analysis of daily or lower frequency macroeconomic and financial data. The previous NSF-sponsored research (award SES-9730440) has been at the forefront of these developments. Many of the ideas and methodologies put forth in our various papers have already been successfully implemented and applied by other researchers and finance practitioners in academia, government, and the private sector. Most immediately, our findings have allowed for the construction of more accurate financial market volatility forecasts and ex-post volatility measurements. Our proposed research agenda in turn holds the promise of improved procedures for risk management, monitoring, and oversight, and should also result in a deeper understanding concerning the efficiency of markets and the effectiveness of different macroeconomic policies. The general results of the proposed activity should therefore be of relevance to applied macroeconomists, time series econometricians, financial researchers, regulators, and practitioners alike.

计算机化通信网络和自动化交易执行系统的出现导致最近可以获得许多不同金融市场和工具的实时价格和信息变量。该项目旨在扩大从这一新的丰富数据源中提取有关重要经济现象的有用信息的能力。 具体而言，高频数据有希望提供：㈠更好地了解导致重要价格变动的信息类型及其与基本市场微观结构的关系; ㈡更深入地了解市场的运作和各种宏观经济政策的有效性; ㈢制定新的和更准确的风险衡量标准;以及（iv）有关长期日内波动依赖性的重要信息，这些信息在资产定价和风险管理中发挥着关键作用。 与此同时，越来越清楚的是，对高频数据进行令人满意的实证分析提出了许多独特和具有挑战性的问题，需要开发新的建模范式和专门程序，这些范式和程序与传统时间序列计量经济学中使用的技术有关，涉及日常或较低频率的宏观经济和金融数据的分析。之前NSF赞助的研究（SES-9730440）一直处于这些发展的最前沿。我们在各种论文中提出的许多想法和方法已经被学术界、政府和私营部门的其他研究人员和金融从业人员成功地实施和应用。最直接的是，我们的研究结果允许构建更准确的金融市场波动性预测和事后波动性测量。我们提出的研究议程反过来又有望改进风险管理、监测和监督程序，并且还应该加深对市场效率和不同宏观经济政策有效性的了解。因此，拟议活动的一般结果应与应用宏观经济学家、时间序列计量经济学家、金融研究人员、监管机构和从业人员等有关。