|
|
 |
 |
| |
 Printable version |
Statistical analysis of a prognostic study |
Bulletin du Cancer. Volume 88, Number 8, 805-10, Août 2001, Note technique
|
 Résumé
Article gratuit
|
Author(s) : Agnès Laplanche, Cédric Mahé |
Summary : Prognostic studies aim to stress and quantify the effect of some individual characteristics on the evolution of an illness. Statistically speaking, most of the time, a prognostic study relying on a censored endpoint can be summarized in building a Cox model. Even though they are often encountered in clinical research or in epidemiology, prognostic studies are rarely reliable and there is no real consensus on the way to perform them. The aim of this article is to give some directions regarding the analysis of such studies. For illustration purpose, this paper relies on commented results from a study in oncology. |
Keywords : prognostic studies, survival analysis, Cox model. |
|
