Chan, K. W. & Yau, C. Y. (2017). Automatic Optimal Batch Size Selection for Recursive Estimators of Time-Average Covariance Matrix. Journal of the American Statistical Association, 112, 1076-1089.

Abstract:

The time-average covariance matrix (TACM) Σ:=∑_k∈ℤΓ_k , where Γ_k is the auto-covariance function, is an important quantity for the inference of the mean of an ℝ^d-valued stationary process (d ⩾ 1). This article proposes two recursive estimators for Σ with optimal asymptotic mean square error (AMSE) under different strengths of serial dependence. The optimal estimator involves a batch size selection, which requires knowledge of a smoothness parameter ϒ_β:=∑_k∈ℤ|k|^β Γ_{k ,} for some β. This article also develops recursive estimators for ϒ_β. Combining these two estimators, we obtain a fully automatic procedure for optimal online estimation for Σ. Consistency and convergence rates of the proposed estimators are derived. Applications to confidence region construction and Markov chain Monte Carlo convergence diagnosis are discussed. Supplementary materials for this article are available online.

• Main Paper (Last Update: 21 Jun 2016)
• Supplementary Note
• R-packages
  • Version 2.1 (Faster)
  • Version 3.1 (More General)
• Presentation Slides (The 4th IMS - Asia Pacific Rim Meeting, 27-30 June 2016)
• Official Link