Censored linear model in high dimensions

TL;DR

This paper introduces a new estimator for high-dimensional censored linear models with left-censored data, providing theoretical guarantees and extending the applicability of penalized regression techniques in complex data scenarios.

Contribution

It develops a novel estimator for high-dimensional censored linear models and derives non-asymptotic oracle inequalities, addressing a gap in theoretical understanding.

Findings

Proposed a new estimator for high-dimensional censored data.

Derived non-asymptotic oracle inequalities for the estimator.

Extended penalized regression methods to censored high-dimensional settings.

Abstract

Censored data are quite common in statistics and have been studied in depth in the last years. In this paper we consider censored high-dimensional data. High-dimensional models are in some way more complex than their low-dimensional versions, therefore some different techniques are required. For the linear case appropriate estimators based on penalized regression, have been developed in the last years. In particular in sparse contexts the $l_1$-penalised regression (also known as LASSO) performs very well. Only few theoretical work was done in order to analyse censored linear models in a high-dimensional context. We therefore consider a high-dimensional censored linear model, where the response variable is left-censored. We propose a new estimator, which aims to work with high-dimensional linear censored data. Theoretical non-asymptotic oracle inequalities are derived.