Robust Variable Selection under Cellwise Contamination
arXiv:2110.12406
Abstract
Cellwise outliers are widespread in data and traditional robust methods may fail when applied to datasets under such contamination. We propose a variable selection procedure, that uses a pairwise robust estimator to obtain an initial empirical covariance matrix among the response and potentially many predictors. Then we replace the primary design matrix and the response vector with their robust counterparts based on the estimated covariance matrix. Finally, we adopt the adaptive Lasso to obtain variable selection results. The proposed approach is robust to cellwise outliers in regular and high dimensional settings and empirical results show good performance in comparison with recently proposed alternative robust approaches, particularly in the challenging setting when contamination rates are high but the magnitude of outliers is moderate. Real data applications demonstrate the practical utility of the proposed method.
arXiv comment17 pages, 4 figures
References in corpus (8)
- High-dimensional regression with noisy and missing data: Provable guarantees with nonconvexity
- Sparse least trimmed squares regression for analyzing high-dimensional large data sets
- Propagation of outliers in multivariate data
- Robust estimation of precision matrices under cellwise contamination
- Fast robust correlation for high-dimensional data
- The shooting S-estimator for robust regression
- Robust regression estimation and inference in the presence of cellwise and casewise contamination
- Outlyingness: why do outliers lie out?