The robust autocovariance matrix estimation (rcov) R package provides
a series of tools to obtain the robust autocovariance matrix estimators.
Its original purpose was to be a support to the paper [“Nonasymptotic
theories for tail-robust autocovariance matrix estimation methods”] but
can obviously be used for time series analysis in general. More
specifically, the package provides tools with the following features:
- Simulation of multivariate stationary time series from linear process model and VAR(1) model.
- Robust estimation of mean vectors for high-dimensional stationary time series.
- Robust estimation of autocovariance matrices for high-dimensional stationary time series.
- Robustification parameter selection based on the block-wise cross-validation.
The rcov package is available on GitHub. You can install the stable
version of the rcov package with:
# Install dependencies
install.packages(c("RcppArmadillo","devtools","knitr","rmarkdown"))
# Install the package from GitHub
devtools::install_github("HaotianXu/rcov")The setup to obtain the development version of rcov is platform
dependent.
The license this source code is released under is the GNU AFFERO GENERAL PUBLIC LICENSE (AGPL) v3.0. Please see the LICENSE file for full text. Otherwise, please consult TLDR Legal or GNU which will provide a synopsis of the restrictions placed upon the code.