报告人：刘广应教授，南京审计大学，

时间：2023-04-19星期三晚19:30-20:30

腾讯会议号: 608-677-947

邀请人：金融数学研究室

摘要：This paper proposes a novel variation-ratio test for the presence of volatility jumps using high frequency data with microstructure noise. Under the null hypothesis that the volatility process is a continuous semimartingale, the test statistic is asymptotically normal. Under the alternative hypothesis that the volatility process jumps, the test statistic diverges to infinity at rate n^{1/4-\tau} for arbitrarily small $\tau>0$, which is faster than the best rate (close to n^{1/8} in the semimartingale setup) available in the literature, where n is the sampling frequency. Simulation results corroborate our theoretical findings. Empirical results show that our test fails to reject the null hypothesis for most of the ninety US stocks under study except for quite a small portion of them. This is a joint work with Yang Li and Zhiyuan Zhang.

个人简介：刘广应，教授，博士生导师，复旦大学博士，浙江大学博士后，香港科技大学访问学者，现为南京审计大学金融数学系主任，江苏省“青蓝工程”学术带头人，中国现场统计研究会旅游大数据学会理事、中国管理科学与工程学会理事、中国管理科学与工程学会金融计量与风险管理分会理事、江苏省概率统计协会理事。研究领域与兴趣：金融高频数据、应用统计、深度学习等。荣获第一届统计科学技术进步奖一等奖、江苏省应用统计学会优秀成果一等奖等奖项，在统计学权威期刊Journal of the American Statistical Association，Journal of Econometrics，Journal of Business & Economic Statistics，《中国科学》《统计研究》等国内外杂志发表或录用论文30多篇。主持2项国家自然科学基金项目、1项国家社会科学基金项目、省部级课题10余项。