Sparse High-Dimensional Vector Autoregressive Bootstrap
Econometrics
2025-05-14 v2 Statistics Theory
Methodology
Statistics Theory
Abstract
We introduce a high-dimensional multiplier bootstrap for time series data based on capturing dependence through a sparsely estimated vector autoregressive model. We prove its consistency for inference on high-dimensional means under two different moment assumptions on the errors, namely sub-gaussian moments and a finite number of absolute moments. In establishing these results, we derive a Gaussian approximation for the maximum mean of a linear process, which may be of independent interest.
Cite
@article{arxiv.2302.01233,
title = {Sparse High-Dimensional Vector Autoregressive Bootstrap},
author = {Robert Adamek and Stephan Smeekes and Ines Wilms},
journal= {arXiv preprint arXiv:2302.01233},
year = {2025}
}