Penalized full likelihood approach to variable selection for Cox’s regression model under nested case–control sampling
- 7 May 2019
- journal article
- research article
- Published by Springer Science and Business Media LLC in Lifetime Data Analysis
- Vol. 26 (2), 292-314
- https://doi.org/10.1007/s10985-019-09475-z
Abstract
Assuming Cox’s regression model, we consider penalized full likelihood approach to conduct variable selection under nested case–control (NCC) sampling. Penalized non-parametric maximum likelihood estimates (PNPMLEs) are characterized by self-consistency equations derived from score functions. A cross-validation method based on profile likelihood is used to choose the tuning parameter within a family of penalty functions. Simulation studies indicate that the numerical performance of (P)NPMLE is better than weighted partial likelihood in estimating the log-relative risk and in identifying the covariates and the model, under NCC sampling. LASSO performs best when cohort size is small; SCAD performs best when cohort size is large and may eventually perform as well as the oracle estimator. Using the SCAD penalty, we establish the consistency, asymptotic normality, and oracle properties of the PNPMLE, as well as the sparsity property of the penalty. We also propose a consistent estimate of the asymptotic variance using observed profile likelihood. Our method is illustrated to analyze the diagnosis of liver cancer among those in a type 2 diabetic mellitus dataset who were treated with thiazolidinediones in Taiwan.Keywords
Funding Information
- Ministry of Science and Technology, Taiwan (MOST-105-2319-B400-002)
This publication has 26 references indexed in Scilit:
- Association of thiazolidinediones with liver cancer and colorectal cancer in type 2 diabetes mellitusHepatology, 2012
- Principled sure independence screening for Cox models with ultra-high-dimensional covariatesJournal of Multivariate Analysis, 2012
- Diabetes and CancerDiabetes Care, 2010
- Cox regression model with time-varying coefficients in nested case-control studiesBiostatistics, 2010
- Epidemiological aspects of neoplasms in diabetesActa Diabetologica, 2010
- Sure Independence Screening for Ultrahigh Dimensional Feature SpaceJournal of the Royal Statistical Society Series B: Statistical Methodology, 2008
- Nested case–control data utilized for multiple outcomes: a likelihood approach and alternativesStatistics in Medicine, 2008
- Usage of the claim database of national health insurance programme for analysis of cisapride‐erythromycin co‐medication in TaiwanPharmacoepidemiology and Drug Safety, 2006
- An asymptotic theory for the nonparametric maximum likelihood estimator in the Cox gene modelBernoulli, 2005
- Maximum likelihood estimation for Cox's regression model under nested case-control samplingBiostatistics, 2004