科研交流
您的位置>> 首 页 > 科研交流 > 学术交流 > 正文
学术交流

数学学院、所2019年系列学术活动(第162场):李东 清华大学统计学研究中心副教授

发表于: 2019-09-19 15:01  点击:

报告题目:Non-standard inference for augmented double autoregressive models with null volatility coefficients

报 告 人:李东 清华大学统计学研究中心副教授

报告时间:2019921日下午1540-1640

报告地点:数学楼 629

报告摘要:

This paper considers an augmented double autoregressive (DAR) model, which allows null volatility coefficients to circumvent the over-parameterization problem in the DAR model. Since the volatility coefficients might be on the boundary, the statistical inference methods based on the Gaussian quasi-maximum likelihood estimation (GQMLE) become non-standard, and their asymptotics require the data to have a finite sixth moment, which narrows applicable scope in studying heavy-tailed data. To overcome this deficiency, this paper develops a systematic statistical inference procedure based on the self-weighted GQMLE for the augmented DAR model. Specifically, we find except for the Lagrange multiplier test statistic, asymptotics for both the Wald and the quasi-likelihood ratio test statistics are non-standard. In addition, a new portmanteau test based on self-weighted residuals is proposed with non-standard asymptotics. The entire procedure is valid as long as the data is stationary, and its usefulness is illustrated by simulation studies and one real example.

报告人简介:

李东,清华大学统计学研究中心副教授,2010年毕业于香港科技大学,2013年加入清华大学。主要研究兴趣:非线性时间序列分析,金融计量学,网络数据分析与大数据。目前担任全国工业统计学教学研究会常务理事,中国青年统计学家协会常务理事,中国现场统计研究会计算统计分会理事,北京应用统计学会理事。主持国际自然科学基金委面上项目2项,参与面上项目1项;结题青年基金项目1项。发表论文二十余篇,其中多篇论文发表在Journal of Econometrics, JBES, Econometric Theory, Biometrika等杂志上。