Power analysis for longitudinal trials

点击翻译按钮获取中文摘要

DESCRIPTION (provided by applicant): Longitudinal trials are trials in which researchers track outcomes over a period of time. These trials play a prominent role in many fields including drug abuse, aging, medicine, social science, and education. Longitudinal studies, by their nature, often address issues that have important implications for long-term health and development. Also, because these studies are often seen as definitive, their results may have a substantial impact on policy. There have been more than 50,000 of these studies published, and the use of this design has been increasing in recent years. The statistical procedures required to plan and to analyze a longitudinal trial are substantially more complex than those used for simple randomized trials. Popular software packages such as SPSS, SAS, and Stata include modules for the analysis of longitudinal trials, and the vast majority of these trials are analyzed using these kinds of modules. By contrast, there is no commercial software to compute power for these trials, and the use of proper techniques to compute power when these studies are being planned is extremely rare. In most cases researchers compute power by ignoring the longitudinal aspect of the study and using techniques intended for simple randomized trials. This is a serious problem because this approach can yield estimates of power that are substantially in error. The goal of this project is to develop software to compute power for longitudinal studies. The program will work with an array of study designs, and it will incorporate a sophisticated user interface to address the kinds of real-world issues that must be addressed in a power analysis. On the input side, it will allow users to enter the kinds of data that they are likely to have, and to do so using a clear and intuitive interface. On the output side the program will create tables and graphs that allow the user to quickly assess the impact of all assumptions, and to determine how changes in the design would affect power and costs.