Robust feature screening for high-dimensional survival data

Meiling Hao, Yuanyuan Lin, Xianhui Liu, Wenlu Tang

Research output: Journal article publicationJournal articleAcademic researchpeer-review

2 Citations (Scopus)


Ultra-high dimensional data arise in many fields of modern science, such as medical science, economics, genomics and imaging processing, and pose unprecedented challenge for statistical analysis. With such rapid-growth size of scientific data in various disciplines, feature screening becomes a primary step to reduce the high dimensionality to a moderate scale that can be handled by the existing penalized methods. In this paper, we introduce a simple and robust feature screening method without any model assumption to tackle high dimensional censored data. The proposed method is model-free and hence applicable to a general class of survival models. The sure screening and ranking consistency properties without any finite moment condition of the predictors and the response are established. The computation of the proposed method is rather straightforward. Finite sample performance of the newly proposed method is examined via extensive simulation studies. An application is illustrated with the gene association study of the mantle cell lymphoma.

Original languageEnglish
Pages (from-to)979-994
Number of pages16
JournalJournal of Applied Statistics
Issue number6
Publication statusPublished - 26 Apr 2019
Externally publishedYes


  • Censored data
  • feature screening
  • high dimension
  • robustness
  • survival analysis

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty


Dive into the research topics of 'Robust feature screening for high-dimensional survival data'. Together they form a unique fingerprint.

Cite this