题目：Inference for asymmetric exponentially weighted moving average model
主讲：李东
时间：2017年11月24日 15:30-16:30
地点：明德主楼1030
摘要：
The exponentially weighted moving average (EWMA) model in ``Risk-Metrics`` has been a benchmark for controlling and forecasting risks in financial operations. However, it is incapable of capturing the asymmetric volatility effect and the heavy-tailed innovation, which are two important stylized features of financial returns. We propose an asymmetric EWMA model driven by the Student`s t distributed innovations to take these two stylized features into account. We find that when the top Lyapunov exponent is zero, the asymmetric EWMA model has a stable sample path to match the real data. Moreover, we study the entire statistical inference procedure of the asymmetric EWMA model, including the maximum likelihood estimation and the tests for the stability of the model, the absence of the drift term, the asymmetry of the model, and the model diagnostic checking, respectively. The performance of this inference procedure is examined by the simulated data.
简介：
李东，副教授，目前任职于清华大学统计学研究中心. 2010年毕业于香港科技大学，2013年加入清华大学. 主要研究方向：非线性时间序列分析、网络与大数据、函数型数据分析和时空模型等,目前发表论文20余篇. 担任北京应用统计学会首届理事和中国现场统计研究会计算统计分会理事.