|
Abstract:
|
Traditional methods of sample size and power calculations in clinical trials with a time-to-event end point are based on the logrank test (and its variations), Cox proportional hazards (PH) assumption, and comparison of means of two exponential distributions. Of these, calculation based on PH assumption is the most popular as it allows adjusting for the effect of one or more covariates. However, there are situations when the assumption of proportional hazards in designing a trial may not be appropriate. When it is known through previously conducted observational studies that there is a rapid decline in the survival curve for a control group, a design based on the PH assumption may promise only a minor statistical improvement for the treatment group that is not practically meaningful. For such scenarios, a clinical trial design based on the concept of Relative Time using the Generalized Gamma Ratio distribution is proposed. Simulation studies are conducted to identify the situations in which such a design will be beneficial as compared to the standard design. A real life example with hemorrhagic stroke patients demonstrates the practical usefulness of this approach.
|
