This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.
|CE_27T||Wed, 8/4/2010, 10:00 AM - 11:45 AM||CC-8 (East)|
|Power Analysis: A Simple and Effective Approach — Continuing Education CTW|
|ASA , Biostat, Inc.|
|Instructor(s): Michael Borenstein, Biostat, Inc., Hannah Rothstein|
|Power analysis is the process of finding the optimal sample size for a planned study. In this workshop we explain the process of power analysis and show how to use it to plan studies and to write grant applications. Power is determined by such factors as the magnitude of the treatment effect, the sample size, and the criterion for statistical significance. The goal of the power analysis is to consider a series of values for factors that we cannot control "(What if the treatment reduces the risk of death by 10% or by 20%") and for factors that we can control ("What if the study runs for two years rather than three"), to find a cost-effective approach. We do this with graphs that allow the researcher to consider a range of options, and find the one that strikes the optimal balance of cost and power. We will show how to do this using the best-selling program Power And Precision. The workshop is recommended for persons new to power analysis, to people frustrated by power analysis, and especially for people who need to perform power analysis for survival studies or for cluster-randomized trials.|