Daniela Dunkler1, Michael Schemper, Georg Heinze. 1. Section of Clinical Biometrics, Center for Medical Statistics, Informatics and Intelligent Systems, Medical University of Vienna, 1090 Vienna, Austria.
Abstract
MOTIVATION: Univariate Cox regression (COX) is often used to select genes possibly linked to survival. With non-proportional hazards (NPH), COX could lead to under- or over-estimation of effects. The effect size measure c=P(T(1)<T(0)), i.e. the probability that a person randomly chosen from group G(1) dies earlier than a person from G(0), is independent of the proportional hazards (PH) assumption. Here we consider its generalization to continuous data c' and investigate the suitability of c' for gene selection. RESULTS: Under PH, c' is most efficiently estimated by COX. Under NPH, c' can be obtained by weighted Cox regression (WHE) or a novel method, concordance regression (CON). The least biased and most stable estimates were obtained by CON. We propose to use c' as summary measure of effect size to rank genes irrespective of different types of NPH and censoring patterns. AVAILABILITY: WHE and CON are available as R packages. CONTACT: georg.heinze@meduniwien.ac.at SUPPLEMENTARY INFORMATION: Supplementary Data are available at Bioinformatics online.
MOTIVATION: Univariate Cox regression (COX) is often used to select genes possibly linked to survival. With non-proportional hazards (NPH), COX could lead to under- or over-estimation of effects. The effect size measure c=P(T(1)<T(0)), i.e. the probability that a person randomly chosen from group G(1) dies earlier than a person from G(0), is independent of the proportional hazards (PH) assumption. Here we consider its generalization to continuous data c' and investigate the suitability of c' for gene selection. RESULTS: Under PH, c' is most efficiently estimated by COX. Under NPH, c' can be obtained by weighted Cox regression (WHE) or a novel method, concordance regression (CON). The least biased and most stable estimates were obtained by CON. We propose to use c' as summary measure of effect size to rank genes irrespective of different types of NPH and censoring patterns. AVAILABILITY: WHE and CON are available as R packages. CONTACT: georg.heinze@meduniwien.ac.at SUPPLEMENTARY INFORMATION: Supplementary Data are available at Bioinformatics online.
Authors: Ingrid Pabinger; Nick van Es; Georg Heinze; Florian Posch; Julia Riedl; Eva-Maria Reitter; Marcello Di Nisio; Gabriela Cesarman-Maus; Noémie Kraaijpoel; Christoph Carl Zielinski; Harry Roger Büller; Cihan Ay Journal: Lancet Haematol Date: 2018-06-07 Impact factor: 18.959
Authors: B Goeppert; L Frauenschuh; M Zucknick; A Stenzinger; M Andrulis; F Klauschen; K Joehrens; A Warth; M Renner; A Mehrabi; M Hafezi; A Thelen; P Schirmacher; W Weichert Journal: Br J Cancer Date: 2013-10-17 Impact factor: 7.640