Identification of Outlying Observations with Quantile Regression for Censored Data

TL;DR

This paper introduces three novel outlier detection algorithms based on censored quantile regression, addressing the lack of methods for censored data, and demonstrates their effectiveness through simulations and real cancer data analysis.

Contribution

The paper develops and evaluates three new outlier detection algorithms specifically designed for censored data, including a novel approach to improve detection accuracy.

Findings

Algorithms perform well in simulation studies

Effective outlier detection demonstrated on cancer data

R package OutlierDC available for implementation

Abstract

Outlying observations, which significantly deviate from other measurements, may distort the conclusions of data analysis. Therefore, identifying outliers is one of the important problems that should be solved to obtain reliable results. While there are many statistical outlier detection algorithms and software programs for uncensored data, few are available for censored data. In this article, we propose three outlier detection algorithms based on censored quantile regression, two of which are modified versions of existing algorithms for uncensored or censored data, while the third is a newly developed algorithm to overcome the demerits of previous approaches. The performance of the three algorithms was investigated in simulation studies. In addition, real data from SEER database, which contains a variety of data sets related to various cancers, is illustrated to show the usefulness of our methodology. The algorithms are implemented into an R package OutlierDC which can be conveniently employed in the \proglang{R} environment and freely obtained from CRAN.