Sample size for survival trials allowing for non-proportional hazards, loss to follow-up and cross-over

Sophie Barthel - Statistical Consultant, FSB Medical LTD

This talk presents a general framework for sample size calculation in survival studies based on comparing two or more survival distributions using the logrank test. Incorporated within this framework are the consideration of non-uniform staggered patient entry, non-proportional hazards, loss to follow-up and treatment changes including cross-over between treatment arms. The framework is very general in nature and is based on using piecewise exponential distributions to model the survival distributions.

The presentation will illustrate the use of the approach and explore its extension to prediction of power during the course of a trial. Software implemented in STATA is freely available.