Research of Jump Durations for CSI300 Index Futures based on Realized Volatility and Improved ACH Models

被引：0

作者：

Chen Sheng-li ^{[1
]}

Li Yi-jun ^{[1
]}

Guan Tao ^{[1
]}

机构：

[1] Harbin Inst Technol, Sch Management, Harbin 150001, Heilongjiang, Peoples R China

来源：

2016 23RD ANNUAL INTERNATIONAL CONFERENCE ON MANAGEMENT SCIENCE & ENGINEERING, VOLS. I AND II | 2016年

基金：

中国国家自然科学基金;

关键词：

Realized kernel; Median realized volatility; Jump duration; ACH models; AUTOREGRESSIVE CONDITIONAL DURATION; TIME; RETURNS; PRICES; IMPACT; RISK;

D O I：

暂无

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

we construct the ADS jump detection based on realized kernel and median realized volatility. The realized volatility of CSI300 index futures is decomposed into jump volatility and continuous volatility. Augmented ACH models including week effect ACH model and intraday ACH model are proposed to describe the dynamic dependency of jump durations. Numerous empirical studies were conducted, drawing the conclusions: daily jumps exhibit weekday effects, while intraday jumps display intraday effects, jumps and jump durations exhibit non-normality and self-correlation Our augmented ACH models can interpret the dynamic dependency of jump durations very well, and the hazard rate of augmented ACH models is volatile and sensitive. This paper presents useful conclusions for investors and regulator to understand the market volatility and grasp the market risk.

引用

页码：1369 / 1376

页数：8