Group and within-group variable selection for competing risks data
Variable selection in the presence of grouped variables is troublesome for competing risks data: while some recent methods deal with group selection only, simultaneous selection of both groups and within-group variables remains largely unexplored. In this context, we propose an adaptive group bridge method, enabling simultaneous selection both within and between groups, for competing risks data. The adaptive group bridge is applicable to independent and clustered data. It also allows the number of variables to diverge as the sample size increases. We show that our new method possesses excellent asymptotic properties, including variable selection consistency at group and within-group levels. We also show superior performance in simulated and real data sets over several competing approaches, including group bridge, adaptive group lasso, and AIC / BIC-based methods.
KeywordsAdaptive penalty Clustered data Competing risks data Group bridge
The US National Cancer Institute (U24CA076518) partially supported this work. The authors would like to thank the Associate Editor and two reviewers for their helpful comments that significantly improved the paper.
- Fu Z (2015) crrp: Penalized variable selection in competing risks regression. http://CRAN.R-project.org/package=crrp, r package version 1.0
- Fu Z, Parikh CR, Zhou B (2016a) Penalized variable selection in competing risks regression. Lifetime Data Anal. doi: 10.1007/s10985-016-9362-3
- Fu Z, Ma S, Lin H, Parikh CR, Zhou B (2016b) Penalized variable selection for multi-center competing risks data. Stat Biosci. doi: 10.1007/s12561-016-9181-9
- Rubio MT, Labopin M, Blaise D et al (2015) The impact of graft-versus-host disease prophylaxis in reduced-intensity conditioning allogeneic stem cell transplant in acute myeloid leukemia: a study from the acute leukemia working party of the European group for blood and marrow transplantation. Haematologica 100:683–689CrossRefGoogle Scholar
- Seetharaman I (2013) Consistent bi-level variable selection via composite group bridge penalized regression. Master’s thesis, Kansas State University, KS, USAGoogle Scholar
- Varadhan R, Kuk D (2015) crrstep: Stepwise covariate selection for the Fine and Gray competing risks regression model. http://CRAN.R-project.org/package=crrstep, r package version 2015-2.1