Sparse boosting for high‐dimensional survival data with varying coefficients. (19th November 2017)

• Record Type: Journal Article
• Authors: Yue, Mu; Li, Jialiang; Ma, Shuangge
• Is Part Of: Statistics in medicine. Volume 37:Number 5(2018)
• Page Start: 789
• Page End: 800
• Publication Date: 2017-11-19
• Subjects: accelerated failure time model -- boosting -- high‐dimensional data -- minimum description length -- varying‐coefficient model; Medical statistics -- Periodicals; Statistique médicale -- Périodiques; Statistiques médicales -- Périodiques; 610.727
• DOI: 10.1002/sim.7544
• Languages: English
• ISSNs: 0277-6715

Abstract

Abstract : Motivated by high‐throughput profiling studies in biomedical research, variable selection methods have been a focus for biostatisticians. In this paper, we consider semiparametric varying‐coefficient accelerated failure time models for right censored survival data with high‐dimensional covariates. Instead of adopting the traditional regularization approaches, we offer a novel sparse boosting (Sparse L 2 Boosting) algorithm to conduct model‐based prediction and variable selection. One main advantage of this new method is that we do not need to perform the time‐consuming selection of tuning parameters. Extensive simulations are conducted to examine the performance of our sparse boosting feature selection techniques. We further illustrate our methods using a lung cancer data analysis.