Asymptotically Normal and Efficient Estimation of Covariate-Adjusted Gaussian Graphical Model

• 成果类型: Article
• 署名作者: Chen, Mengjie; Ren, Zhao; Zhao, Hongyu; Zhou, Harrison
• 署名单位: University of North Carolina; University of North Carolina Chapel Hill; Pennsylvania Commonwealth System of Higher Education (PCSHE); University of Pittsburgh; Yale University; Yale University
• 刊物名称: JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
• ISSN/ISSBN: 0162-1459
• DOI: 10.1080/01621459.2015.1010039
• 发表日期: 2016
• 页码: 394-406
• 关键词: precision matrix estimation; Optimal Rates; SPARSE; regression; Lasso; CONVERGENCE; RECOVERY; genomics

摘要

We propose an asymptotically normal and efficient procedure to estimate every finite subgraph for covariate-adjusted Gaussian graphical model. As a consequence, a confidence interval as well as p-value can be obtained for each edge. The procedure is tuning-free and enjoys easy implementation and efficient computation through parallel estimation on subgraphs or edges. We apply the asymptotic normality result to perform support recovery through edge-wise adaptive thresholding. This support recovery procedure is called ANTAC, standing for asymptotically normal estimation with thresholding after adjusting covariates. ANTAC outperforms other methodologies in the literature in a range of simulation studies. We apply ANTAC to identify gene-gene interactions using an eQTL dataset. Our result achieves better interpretability and accuracy in comparison with a state-of-the-art method. Supplementary materials for the article are available online.