國立中央大學統計研究所學術演講主講人：郭美惠教授（國立中山大學應用數學系）講題：Volatility of high frequency trading : estimation and online monitoring 時間：103 年 10 月 28 日（星期二）上午 11：00 ～ 12：00 地點：中央大學鴻經館 M605室茶會：上午 10：30 ～11：00 地點：鴻經館 510 室 ABSTRACT High-frequency trading (HFT) has often proven to be particularly profitable, yet it has also been the subject of much public debate. For instance, U.S. Securities and Exchange Commission and the Commodity Futures Trading Commission reported that HFT strategies may have contributed to subsequent volatility of the 2010 Flash Crash. Volatility is an important factor of high frequency trading strategy and a crucial measure of market performance. In this talk, I will discuss volatility estimation and monitoring for high frequency transaction data. In the first part, we propose a quadratic unbiased estimator of the integrated volatility for stochastic volatility models with microstructure noise. The proposed estimator minimizes the finite sample variance in the class of quadratic estimators based on symmetric Toeplitz matrices. We show the proposed estimator has an asymptotic mixed normal distribution with convergence rate O p (n −1/4 ) and achieves the maximum likelihood estimator efficiency for constant volatility case. In the second part, we consider the problem of monitoring the high frequency volatility. Define the market reaction portion (MRP) as the ratio of the integrated volatility to the observed squared returns. Time series models are fitted to the MRP data obtained from 70-minute returns of NYSE tick-to-tick transaction data. Both retrospective and dynamic online control charts of the MRP data are established based on the fitted time series models. The McNemar test supports that the dynamic online control charts have the same power of detecting out of control events as the retrospective control charts. ◎敬請張貼歡迎參加◎