High-dimensional time series data appear in many scientific areas in the current data-rich environment. Analysis of such data poses new challenges to data analysts because of not only the complicated dynamic dependence between the series, but also the existence of aberrant observations, such as missing values, contaminated observations, and heavy-tailed distributions. For high-dimensional vector autoregressive (VAR) models, we introduce a unified estimation procedure that is robust to model misspecification, heavy-tailed noise contamination, and conditional heteroscedasticity. The proposed methodology enjoys both statistical optimality and computational efficiency, and can handle many popular high-dimensional models, such as sparse, reduced-rank, banded, and network-structured VAR models. With proper regularization and data truncation, the estimation convergence rates are shown to be almost optimal in the minimax sense under a bounded $(2+2\epsilon)$-th moment condition. When $\epsilon\geq1$, the rates of convergence match those obtained under the sub-Gaussian assumption. Consistency of the proposed estimators is also established for some $\epsilon\in(0,1)$, with minimax optimal convergence rates associated with $\epsilon$. The efficacy of the proposed estimation methods is demonstrated by simulation and a U.S. macroeconomic example.
翻译:高维时间序列数据出现在当前数据丰富环境中的许多科学领域。对这些数据的分析给数据分析员带来了新的挑战,不仅因为系列之间复杂的动态依赖,而且由于存在异常的观测,例如缺失值、受污染的观测和重尾分布。对于高维矢量自动递减模型,我们引入了一种统一的估算程序,该程序非常有力,可以模拟误差、重尾噪声污染和有条件的超升度。拟议方法既具有统计最佳性,又具有计算效率,并能处理许多广受欢迎的高维模型,例如稀疏、降级、带宽和网络结构的VAR模型。在适当规范化和数据快速转换的情况下,估计趋同率在受约束的 $(2+2\ epsilon)-timatement(美元)-timproducality1美元条件下几乎是最佳的。当美元\eepsilegregality 和美元(美元)下的拟议最优化的IMexcial excial excial excial) excialtial excial excial excializal eximalizalizalizalisalislational as millations (美元) excialismissual) extial amlationalismuplationalmuplations) amlupluplationalmuplationalmationalmational amlational amlus. 。提议,Suplations mismismus. 10 。提议, 和美元 $1 mismismismismismismismlum 和美元的模型的模型。提议的模型的模型的模型的缩缩缩缩缩。提议。