Translator Disclaimer
2015 Confidence intervals for high-dimensional inverse covariance estimation
Jana Janková, Sara van de Geer
Electron. J. Statist. 9(1): 1205-1229 (2015). DOI: 10.1214/15-EJS1031

Abstract

We propose methodology for statistical inference for low-dimensional parameters of sparse precision matrices in a high-dimensional setting. Our method leads to a non-sparse estimator of the precision matrix whose entries have a Gaussian limiting distribution. Asymptotic properties of the novel estimator are analyzed for the case of sub-Gaussian observations under a sparsity assumption on the entries of the true precision matrix and regularity conditions. Thresholding the de-sparsified estimator gives guarantees for edge selection in the associated graphical model. Performance of the proposed method is illustrated in a simulation study.

Citation

Download Citation

Jana Janková. Sara van de Geer. "Confidence intervals for high-dimensional inverse covariance estimation." Electron. J. Statist. 9 (1) 1205 - 1229, 2015. https://doi.org/10.1214/15-EJS1031

Information

Received: 1 March 2014; Published: 2015
First available in Project Euclid: 1 June 2015

zbMATH: 1307.62015
MathSciNet: MR3354336
Digital Object Identifier: 10.1214/15-EJS1031

Subjects:
Primary: 62J07
Secondary: 62F12

Rights: Copyright © 2015 The Institute of Mathematical Statistics and the Bernoulli Society

JOURNAL ARTICLE
25 PAGES


SHARE
Vol.9 • No. 1 • 2015
Back to Top