Group recovery after trimming, and level-free flagging, in robust clusterwise regression
Abstract
Trimming methods for robust clusterwise regression discard a fixed fraction of the data. Too low a level breaks the fit; too generous a level can trim away a small group. We first propose a group-recovery step that can follow any trimming or flagging method: it searches the discarded units for a line, tests whether those near it form a peak rather than a band, and restores the line as a group when the likelihood of Gaussian groups plus uniform noise improves by a margin like that of the Bayesian information criterion. In simulations it repaired the failures of a generous TCLUST-REG level with unequal groups, but not with three or four groups. The second proposal, ESF (exact-subsample flagging), is a flagging procedure without a trimming level: it solves the clusterwise least-squares problem exactly on small subsamples, flags units far from the best fit, and draws later subsamples from the rest. Two constants stand in for the level: a subsample size, set from a lower bound on the smallest group proportion, and a cap on the flagged set. It is meant for data about whose contamination nothing is known: TCLUST-REG at the fixed level 0.30, followed by reweighting and the recovery step, was as accurate as ESF on average up to a fifth of outliers, and higher levels were more accurate beyond. The flagged fraction estimates the contamination only when the errors are close to Gaussian. On taxi fares with known tariffs, ESF found both in every sample.
Related
- OLS Testing with Predictors Scaled to Have Unit Sample Variance, and Similar Results for a Robust Regression Estimator
- Byzantine-Robust Sparse Regression with Missing Covariates
- Robust Local Fréchet Regression: Nonasymptotic Theory and Minimax Optimality
- Robust Error Bounds for Vector-Valued Kernel Ridge Regression
- Evaluation of a robust and asymmetric class of nonlinear regression models under censoring
BibTeX
@misc{orujov2026group,
title = {{Group recovery after trimming, and level-free flagging, in robust clusterwise regression}},
author = {Samir Orujov},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2609.31019},
eprint = {2609.31019},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.31019},
}
RIS
TY - UNPB
TI - Group recovery after trimming, and level-free flagging, in robust clusterwise regression
AU - Samir Orujov
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2609.31019
UR - https://arxiv.org/abs/2609.31019
AB - Trimming methods for robust clusterwise regression discard a fixed fraction of the data. Too low a level breaks the fit; too generous a level can trim away a small group. We first propose a group-recovery step that can follow any trimming or flagging method: it searches the discarded units for a line, tests whether those near it form a peak rather than a band, and restores the line as a group when the likelihood of Gaussian groups plus uniform noise improves by a margin like that of the Bayesian information criterion. In simulations it repaired the failures of a generous TCLUST-REG level with unequal groups, but not with three or four groups. The second proposal, ESF (exact-subsample flagging), is a flagging procedure without a trimming level: it solves the clusterwise least-squares problem exactly on small subsamples, flags units far from the best fit, and draws later subsamples from the rest. Two constants stand in for the level: a subsample size, set from a lower bound on the smallest group proportion, and a cap on the flagged set. It is meant for data about whose contamination nothing is known: TCLUST-REG at the fixed level 0.30, followed by reweighting and the recovery step, was as accurate as ESF on average up to a fifth of outliers, and higher levels were more accurate beyond. The flagged fraction estimates the contamination only when the errors are close to Gaussian. On taxi fares with known tariffs, ESF found both in every sample.
ER -