Autocovariance Estimation via Difference-Based Methods

Provides methods for (auto)covariance/correlation function estimation in change point regression with stationary errors circumventing the pre-estimation of the underlying signal of the observations. Generic, first-order, (m+1)-gapped, difference-based autocovariance function estimator is based on M. Levine and I. Tecuapetla-Gómez (2023) . Bias-reducing, second-order, (m+1)-gapped, difference-based estimator is based on I. Tecuapetla-Gómez and A. Munk (2017) . Robust autocovariance estimator for change point regression with autoregressive errors is based on S. Chakar et al. (2017) . It also includes a general projection-based method for covariance matrix estimation.