Journal article
ORACLE INEQUALITIES AND SELECTION CONSISTENCY FOR WEIGHTED LASSO IN HIGH-DIMENSIONAL ADDITIVE HAZARDS MODEL
Statistica Sinica, Vol.27(4), pp.1903-1920
10/01/2017
DOI: 10.5705/ss.202015.0075
Abstract
The additive hazards model has many applications in high-throughput genomic data analysis and clinical studies. In this article, we study the weighted Lasso estimator for the additive hazards model in sparse, high-dimensional settings where the number of time-dependent covariates is much larger than the sample size. Based on compatibility, cone invertibility factors, and restricted eigenvalues of the Hessian matrix, we establish some non-asymptotic oracle inequalities for the weighted Lasso. Under mild conditions, we show that these quantities are bounded from below by positive constants, thus the compatibility and cone invertibility factors can be treated as positive constants in the oracle inequalities. A multistage adaptive method with weights recursively generated from a concave penalty is presented. We prove a selection consistency theorem and establish an upper bound for dimension of the weighted Lasso estimator.
Details
- Title: Subtitle
- ORACLE INEQUALITIES AND SELECTION CONSISTENCY FOR WEIGHTED LASSO IN HIGH-DIMENSIONAL ADDITIVE HAZARDS MODEL
- Creators
- Haixiang Zhang - Tianjin UniversityLiuquan Sun - Shanghai University of Finance and EconomicsYong Zhou - Shanghai University of Finance and EconomicsJian Huang - University of Iowa
- Resource Type
- Journal article
- Publication Details
- Statistica Sinica, Vol.27(4), pp.1903-1920
- Publisher
- STATISTICA SINICA
- DOI
- 10.5705/ss.202015.0075
- ISSN
- 1017-0405
- eISSN
- 1996-8507
- Number of pages
- 18
- Grant note
- 2014M550861 / China Postdoctoral Science Foundation 11301212; 11401146; 11231010; 11690015; 71331006; 91546202 / National Natural Science Foundation of China 2008DP173182 / Key Laboratory of RCSDS, CAS IRTSHUFE13122402 / Innovative Research Team of Shanghai University of Finance and Economics
- Language
- English
- Date published
- 10/01/2017
- Academic Unit
- Statistics and Actuarial Science
- Record Identifier
- 9984257744502771
Metrics
24 Record Views