Description
When computing power for survival study one must take account not only of the hazard ratio, sample size and alpha, but also the accrual period, followup period, base rate, and attrition. This workshop will show how it is possible to simultaneously consider the impact of these various factors using a new module in the Power and Precision computer program. This program provides a real-time graph of the survival curves, which allows the statistician to ensure that the study is being described properly. It also generates sets of graphs that show how power will vary as any (or several) parameters of the study design are modified. The program also implements a new formula that will compute power by formula (rather than simulation) even when the hazard rate varies over time. Development of this program was funded by the National Institutes of Health (NIMH/SBIR). Attendees should be familiar with survival analysis and power analysis.
|