赋权已实现波动及其长记忆性,最优频率选择  

Weighted realized volatility and its long memory and optimal frequency

作　　者：郭名媛[1] 张世英[1] 

机构地区：[1]天津大学管理学院,天津300072

出　　处：《系统工程学报》2006年第6期568-573,共6页Journal of Systems Engineering

基　　金：国家自然科学基金资助项目(70471050)

摘　　要：已实现波动是针对高频金融时间序列的一种全新的波动度量方法,具有不需要模型和计算方便的优点.本文则对已实现波动进行了改进,提出了另一种更为有效的波动度量方法———赋权已实现波动,并且使得“已实现”波动成为赋权已实现波动的一个特例.通过对上海股票市场的实证研究,说明了赋权已实现波动是优于已实现波动的波动估计量,并且对赋权已实现波动的统计特性进行了分析.同时,在综合考虑微观结构误差和测量误差的基础上选择了最优的高频数据采样频率.Realized volatility is a new measure approach of volatility in high-frequency time series. Realized volatility is model-free and can be computed easily. A more efficient volatility measurement-weighted realized volatility-is put forward, which makes realized volatility b^ome its special case. Through the empirical study on the Shanghai stock market, It is proved that weighted realized volatility is superior to realized volatility. The characteristics of the weighted realized volatility are studied. Optimal frequency is decided based on microstructure error and measure error.

关 键 词：已实现波动 赋权已实现波动 最优采样频率 长记忆性 

分 类 号：F830.91[经济管理—金融学]