Planning Studies accounting for competing risks

Aurélien Latouche (1) , Raphaël Porcher (1)

1 Biostatistique et épidemiologie clinique

Recently, with the growth of statistical developments for competing risks analysis, some methods have been proposed to compute sample size and plan a study in such a framework. These methods differ from a modelling approach: some are based on the Cox regression model for the cause-specific hazard accounting or not for accrual and follow--up period while another deals with the Fine and Gray regression model for the subdistribution hazard of a competing risk. Nonetheless, these formulas rely on similar key parameters, namely the difference one wishes to detect and the proportion of patients who will actually experience the event of interest. Choices for these parameters have a drastic effect on the sample size or equivalently the power. In this work, we compare these approaches and give practical advices for planning studies in a competing risks framework.

Mots clés: Sample Size; competing risks; supremum log--rank; Renyi test

Domaines: Santé publique et épidémiologie

Aurélien Latouche, Raphaël Porcher. Planning Studies accounting for competing risks. 2006. ⟨hal-00116989⟩