Variable selection in the presence of missing data: resampling and imputation
Open Access
- 18 February 2015
- journal article
- research article
- Published by Oxford University Press (OUP) in Biostatistics
- Vol. 16 (3), 596-610
- https://doi.org/10.1093/biostatistics/kxv003
Abstract
In the presence of missing data, variable selection methods need to be tailored to missing data mechanisms and statistical approaches used for handling missing data. We focus on the mechanism of missing at random and variable selection methods that can be combined with imputation. We investigate a general resampling approach (BI-SS) that combines bootstrap imputation and stability selection, the latter of which was developed for fully observed data. The proposed approach is general and can be applied to a wide range of settings. Our extensive simulation studies demonstrate that the performance of BI-SS is the best or close to the best and is relatively insensitive to tuning parameter values in terms of variable selection, compared with several existing methods for both low-dimensional and high-dimensional problems. The proposed approach is further illustrated using two applications, one for a low-dimensional problem and the other for a high-dimensional problem.Keywords
This publication has 15 references indexed in Scilit:
- Bootstrapping Lasso EstimatorsJournal of the American Statistical Association, 2011
- EEBoost: A General Method for Prediction and Variable Selection Based on Estimating EquationsJournal of the American Statistical Association, 2011
- Variable Selection in the Cox Regression Model with Covariates Missing at RandomBiometrics, 2010
- Stability selectionJournal of the Royal Statistical Society Series B: Statistical Methodology, 2009
- Penalized Estimating Functions and Variable Selection in Semiparametric Regression ModelsJournal of the American Statistical Association, 2008
- Variable selection under multiple imputation using the bootstrap in a prognostic studyBMC Medical Research Methodology, 2007
- Imputation and Variable Selection in Linear Regression Models with Missing CovariatesBiometrics, 2005
- Least angle regressionThe Annals of Statistics, 2004
- Missing Data, Imputation, and the BootstrapJournal of the American Statistical Association, 1994
- A new look at the statistical model identificationIEEE Transactions on Automatic Control, 1974