American Statistical Association
We are seeing a dramatic increase in the number of possible components (factors) due to developments in science and technology (internet, web-based surveys, and so on). These changes dictate the need for alternative methods over the commonly used randomized controlled trials studies that can screen a large set of potentially important components in order to identify the important ones quickly and economically. Over the past five years, the NCI-funded Center for Health Communications Research at University of Michigan has developed and implemented a multiphase experimentation strategy for screening new interventions, refining our understanding of their effects, and confirming their superiority over controls. We have adapted this strategy from a similar framework that has been successfully used in engineering applications for many years. In this talk, I will use two web-based studies (Project Quit on smoking cessation and Guide to Decide for studying the effectiveness of specific decision aids in this case for women who are at high risk of breast cancer) to illustrate the methodology and its usefulness.
|Date:||Tuesday, April 1, 2008|
|Time:||3:30 - 4:30 P.M.|
New York State Psychiatric Institute
1051 Riverside Drive
6th Floor Multi-Purpose Room (6602)
New York, New York