The Annals of Statistics
- Ann. Statist.
- Volume 45, Number 6 (2017), 2680-2707.
Structural similarity and difference testing on multiple sparse Gaussian graphical models
We present a new framework on inferring structural similarities and differences among multiple high-dimensional Gaussian graphical models (GGMs) corresponding to the same set of variables under distinct experimental conditions. The new framework adopts the partial correlation coefficients to characterize the potential changes of dependency strengths between two variables. A hierarchical method has been further developed to recover edges with different or similar dependency strengths across multiple GGMs. In particular, we first construct two-sample test statistics for testing the equality of partial correlation coefficients and conduct large-scale multiple tests to estimate the substructure of differential dependencies. After removing differential substructure from original GGMs, a follow-up multiple testing procedure is used to detect the substructure of similar dependencies among GGMs. In each step, false discovery rate is controlled asymptotically at a desired level. Power results are proved, which demonstrate that our method is more powerful on finding common edges than the common approach that separately estimates GGMs. The performance of the proposed hierarchical method is illustrated on simulated datasets.
Ann. Statist., Volume 45, Number 6 (2017), 2680-2707.
Received: February 2016
Revised: January 2017
First available in Project Euclid: 15 December 2017
Permanent link to this document
Digital Object Identifier
Mathematical Reviews number (MathSciNet)
Zentralblatt MATH identifier
Liu, Weidong. Structural similarity and difference testing on multiple sparse Gaussian graphical models. Ann. Statist. 45 (2017), no. 6, 2680--2707. doi:10.1214/17-AOS1539. https://projecteuclid.org/euclid.aos/1513328587
- Structural similarity and difference testing on multiple sparse Gaussian graphical models. The supplementary material includes the proofs of Proposition 3.1, Theorems 3.3–3.5 and Lemmas 6.1–6.3. Also, a part of numerical results in Section 4 are included.