报告地点：行健楼学术活动室526
邀请人：刘正威博士
摘要：In the past four decades, research on count time series has made significant progress, but research on Z-valued time series is relatively rare. Existing Z-valued models are mainly of autoregressive structure, where the use of the rounded operator is very natural. Because of the discontinuity of the rounded operator, the formulation of the corresponding model identifiability conditions and the computation of parameter estimators need special attention. It is also difficult to derive closed-form formulae for crucial stochastic properties. We rediscover a stochastic rounded operator, referred to as mean-preserving rounded, which overcomes the above drawbacks. Then, a novel class of Z-valued ARMA models and its bivariate version based on the new operator is proposed, and the existence of stationary solutions of the models is established. In particular, our model construction avoids identifiability issues such that maximum likelihood estimation is possible.
个人简介：朱复康，吉林大学数学学院教授、博士生导师，吉林国家应用数学中心副主任、概率统计与数据科学系主任。2008年博士毕业，2013年破格晋升教授。主要从事时间序列分析和金融统计的研究，已经在Annals of Applied Statistics、Journal of Business & Economic Statistics、Statistica Sinica、Scandinavian Journal of Statistics、Journal of Time Series Analysis、中国科学-数学等期刊上发表论文多篇，主持国家自然科学基金面上项目3项和青年基金1项。曾获教育部自然科学奖二等奖、吉林省科学技术奖二等奖、吉林省享受省政府津贴专家、长春市有突出贡献专家等奖励，连续三年(2023-2025)入选美国斯坦福大学发布的全球前2%顶尖科学家榜单，获得Journal of Time Series Analysis期刊杰出作者奖。现任吉林省现场统计研究会副理事长，中国现场统计研究会、全国工业统计学教学研究会、中国数学会概率统计分会等学会的理事或常务理事。现任SCI期刊Statistical Papers、Journal of Statistical Computation and Simulation的副主编，是JASA、JRSSB、JBES、AoAS等80余个SCI期刊的匿名审稿人。指导的研究生1人获得吉林省优秀博士学位论文、3人获得吉林省优秀硕士学位论文。
