Annals of Statistics
- Ann. Statist.
- Volume 41, Number 6 (2013), 2948-2978.
Gaussian graphical model estimation with false discovery rate control
Abstract
This paper studies the estimation of a high-dimensional Gaussian graphical model (GGM). Typically, the existing methods depend on regularization techniques. As a result, it is necessary to choose the regularized parameter. However, the precise relationship between the regularized parameter and the number of false edges in GGM estimation is unclear. In this paper we propose an alternative method by a multiple testing procedure. Based on our new test statistics for conditional dependence, we propose a simultaneous testing procedure for conditional dependence in GGM. Our method can control the false discovery rate (FDR) asymptotically. The numerical performance of the proposed method shows that our method works quite well.
Article information
Source
Ann. Statist., Volume 41, Number 6 (2013), 2948-2978.
Dates
First available in Project Euclid: 1 January 2014
Permanent link to this document
https://projecteuclid.org/euclid.aos/1388545674
Digital Object Identifier
doi:10.1214/13-AOS1169
Mathematical Reviews number (MathSciNet)
MR3161453
Zentralblatt MATH identifier
1288.62094
Subjects
Primary: 62H12: Estimation 62H15: Hypothesis testing
Keywords
False discovery rate Gaussian graphical model multiple tests
Citation
Liu, Weidong. Gaussian graphical model estimation with false discovery rate control. Ann. Statist. 41 (2013), no. 6, 2948--2978. doi:10.1214/13-AOS1169. https://projecteuclid.org/euclid.aos/1388545674
Supplemental materials
- Supplementary material: Supplement to “Gaussian graphical model estimation with false discovery rate control”. This supplemental material includes additional numerical results for GFC-Dantizg and GFC-Lasso.Digital Object Identifier: doi:10.1214/13-AOS1169SUPP