A Bernstein-type Inequality for High Dimensional Linear Processes with Applications to Robust Estimation of Time Series Regressions

Abstract

Time series regression models are commonly used in time series analysis. However, in modern real-world applications, serially correlated data with an ultra-high dimension and fat tails are prevalent. This presents a challenge in developing new statistical tools for time series analysis. In this paper, we propose a novel Bernstein-type inequality for high-dimensional linear processes and apply it to investigate two high-dimensional robust estimation problems: (1) time series regression with fat-tailed and correlated covariates and errors, and (2) fat-tailed vector autoregression. Our proposed approach allows for exponential increases in dimension with sample size under mild moment and dependence conditions, while ensuring consistency in the estimation process.

References in corpus (4)

• Large sample behaviour of high dimensional autocovariance matrices
• Regularized estimation of linear functionals of precision matrices for high-dimensional time series
• High Dimensional and Banded Vector Autoregressions
• A Bernstein-type Inequality for Some Mixing Processes and Dynamical Systems with an Application to Learning