报告题目：An Adaptive L2-type Test for High-dimensional White Noise
报告人：常晋源
讲座时间：2026年11月17日（周二） 第一场9:00-10:00 第二场10:30-11:30
地点：综合楼644会议室
报告人简介：
常晋源，西南财经大学光华首席教授、中国科学院数学与系统科学研究院研究员，国家级高层次人才，主要从事大规模复杂数据分析相关的研究，先后担任统计学、计量经济学和运筹优化国际学术期刊Statistica Sinica、Journal of the Royal Statistical Society Series B、Journal of Business & Economic Statistics、Journal of the American Statistical Association和Operations Research的副主编，获得过国务院政府特殊津贴、霍英东教育基金会高等院校青年科学奖一等奖和青年教师奖一等奖、教育部高等学校科学研究优秀成果奖、四川省青年科技奖等奖励，获四川省基础研究领衔科学家专项资助。
报告摘要：
We propose a new L2-type test for white noise which allows the dimension p of the time series to either (i) be a fixed constant, or (ii) diverge with the sample size n. The proposed test statistic exhibits an interesting phase transition, following two different regimes of behavior: p is fixed, and p → ∞. Because identification of the operable regime is difficult, if not impossible in practice, we devise a novel adaptive bootstrap method to construct a unified testing procedure across different phases. Numerical experiments confirm the good finite sample performance of the proposed adaptive L2-type test in comparison to the existing methods in the literature. The proposed testing procedure has been implemented in R package HDTSA.
