Non-asymptotic rate for high-dimensional covariance estimation with non-independent missing observations

DOI10.1016/J.SPL.2019.06.002zbMath1458.62151OpenAlexW2951285098MaRDI QIDQ2322678

Johan Lim, Seongoh Park

Publication date: 5 September 2019

Published in: Statistics \& Probability Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.spl.2019.06.002

zbMATH Keywords

covariance matrixconvergence ratemissing completely at randominverse probability weight estimator

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Estimation in multivariate analysis (62H12) Missing data (62D10)

Related Items (2)

Sparse precision matrix estimation with missing observations ⋮ Estimating high-dimensional covariance and precision matrices under general missing dependence

Cites Work

• Unnamed Item
• High-dimensional covariance matrix estimation with missing observations
• Normal approximation and concentration of spectral projectors of sample covariance
• Minimax rate-optimal estimation of high-dimensional covariance matrices with incomplete data
• Covariance regularization by thresholding
• High-dimensional semiparametric Gaussian copula graphical models
• High-dimensional covariance estimation by minimizing \(\ell _{1}\)-penalized log-determinant divergence
• On the sample covariance matrix estimator of reduced effective rank population matrices, with applications to fPCA
• A Constrainedℓ₁Minimization Approach to Sparse Precision Matrix Estimation
• Estimating structured high-dimensional covariance and precision matrices: optimal rates and adaptive estimation

This page was built for publication: Non-asymptotic rate for high-dimensional covariance estimation with non-independent missing observations