1223 Health Findings and False Discoveries

Saturday, February 20, 2010: 3:30 PM
Room 11A (San Diego Convention Center)
Stanley Young , National Institute of Statistical Sciences, Research Triangle Park, NC

It is a fact that 80-95% of claims made based on observational data fail to replicate when rigorously re-tested. That there are serious problems with the conduct and analysis of observational studies has been known for at least 40 years. There is a need to know how this is technically happening and the reasons why it keeps happening. This area of science is not currently self-correcting. Our idea is to consider the problem from a systems point of view, funding agencies, authors, journal editors. What are the incentives that keep this high level of false claims continuing. I think we now know where to place the blame, and it is not on the scientists.

Previous Presentation | Next Presentation >>