摘要
高频金融数据的分析与建模是金融计量学的一个全新的研究领域.高频数据"日历效应"是金融市场微观结构研究领域的重要发现,但是金融市场微观结构理论主要是从定性的角度研究"日历效应".如何定量地刻画高频数据"日历效应"是进一步深入理解金融市场的关键.论文提出用小波神经网络(WNN)来定量研究高频金融数据"日历效应",实证研究表明小波神经网络(WNN)很好地刻画了"日历效应".
High-frequency financial data analysis and modeling is a new research field in financial econometrics, and the calendar effects are most important discovery in financial market microstructure field. But market microstructure theory is qualitative, how to study calendar effects quantitative is a big problem to know financial market. The paper proposes application of Wavelet Neural Network in high-frequency data calendar effects＇ study, and empirical study shows WNN is good method to describe calendar effects.
出处
《数学的实践与认识》
CSCD
北大核心
2007年第15期1-6,共6页
Mathematics in Practice and Theory
基金
国家自然科学基金(70471050)
