Format

Send to

Choose Destination
Biometrics. 2016 Sep;72(3):760-9. doi: 10.1111/biom.12477. Epub 2016 Jan 28.

A log-rank-type test to compare net survival distributions.

Grafféo N1,2, Castell F3, Belot A4,5,6,7,8, Giorgi R9,10,11.

Author information

1
INSERM, UMR912 "Sciences Économiques et Sociales de la Santé et Traitement de l'Information Médicale" (SESSTIM), F-13006 Marseille, France.
2
Université d'Aix-Marseille, UMR S912, IRD, F-13006 Marseille, France.
3
Université d'Aix-Marseille, CNRS, Centrale Marseille, I2M, UMR 7373, F-13453 Marseille, France.
4
Service de Biostatistique, Hospices Civils de Lyon, F-69003 Lyon, France.
5
Université de Lyon, F-69000 Lyon, France.
6
Université Lyon 1, F-69100 Villeurbanne, France.
7
CNRS, UMR5558, Laboratoire de Biométrie et Biologie Évolutive, Équipe Biostatistique-Santé, F-69100 Villeurbanne, France.
8
Institut de Veille Sanitaire, DMCT, Saint-Maurice, France.
9
INSERM, UMR912 "Sciences Économiques et Sociales de la Santé et Traitement de l'Information Médicale" (SESSTIM), F-13006 Marseille, France. roch.giorgi@univ-amu.fr.
10
Université d'Aix-Marseille, UMR S912, IRD, F-13006 Marseille, France. roch.giorgi@univ-amu.fr.
11
APHM, Hôpital Timone, BIOSTIC, Marseille, France. roch.giorgi@univ-amu.fr.

Abstract

In population-based cancer studies, it is often interesting to compare cancer survival between different populations. However, in such studies, the exact causes of death are often unavailable or unreliable. Net survival methods were developed to overcome this difficulty. Net survival is the survival that would be observed if the disease under study was the only possible cause of death. The Pohar-Perme estimator (PPE) is a nonparametric consistent estimator of net survival. In this article, we present a log-rank-type test for comparing net survival functions (as estimated by PPE) between several groups. We put the test within the counting process framework to introduce the inverse probability weighting procedure as required by the PPE. We built a stratified version to control for categorical covariates that affect the outcome. We performed simulation studies to evaluate the performance of this test and worked an application on real data.

KEYWORDS:

Cancer; Log-rank; Net survival; Pohar-Perme estimator; Stochastic process; Test

PMID:
26821615
DOI:
10.1111/biom.12477
[Indexed for MEDLINE]
Free full text

Supplemental Content

Full text links

Icon for Wiley Icon for London School of Hygiene and Tropical Medicine
Loading ...
Support Center