G. Gomez Melis, M. Gómez-Mateu, M. Bofill Roig
Randomized clinical trials (RCT) are essential for the advance of medical knowledge and patient care. The primary endpoint (PE) measures the clinical evidence and is defined in the protocol of the RCT. Composite endpoints (CE) -union of several relevant endpoints- are often used as the PE in an RCT. The asymptotic relative efficiency (ARE) method is used to quantify the gained efficiency of adding a secondary endpoint to the PE and use, as primary, the CE. We present an overview of CE, introduce the ARE method and illustrate how can be applied by means of CompARE (https://cinna.upc.edu/compare), a web-based tool that computes ARE in terms of interpretable parameters. We study, for time-to-event outcomes, the behaviour of the hazard ratio of a CE, a summary measure of the treatment effect, observe how it varies over time and use CompARE for sample size assessment. We expand the ARE method to binary CE and present a new Relative Efficiency measure for fixed alternative hypotheses.
Palabras clave: Hazard ratio; Randomized clinical trials; Relative efficiency; Sample size computation
Programado
L06.3 Sesión de la Sociedad Española de Biometría
5 de septiembre de 2016 12:55
Aula 21.08
