F.D.A., Nissen [a cardiologist] and G.S.K. [GlaxoSmithKline, the pharma] all come to comparable conclusions regarding increased risk for ischemic events [heart attacks], ranging from 30 percent to 43 percent!
If everyone agrees that taking Avandia, the blockbuster G.S.K. diabetes drug, increases the risk of heart attacks, what's the problem? Why is Avandia still being prescribed? Read this New York Times article to find out.
While this article contains very little science, it is not to be missed by anyone interested in real-life decision-making in our society. For those working in industry, it's better to realize sooner rather than later that getting the analysis right is only the beginning of the end. And that is because the kind of mathematical argument statisticians are trained in is not useful in convincing people who are not similarly trained. This article gives us a rare glimpse behind the scenes: we learn about who the players are, and moreover, we eavesdrop on some of their (secretly recorded) conversation.
This article mirrors the perspective that I take in putting together Numbers Rule Your World. There are people in these stories, not all of them are statisticians, and they shape the final decisions. The math gets us to the beginning of the end, but the path to the end is often tortuous, and sometimes, even mathematical optimality has to take a back seat.
Update [3/29/2010]: This post has found a new life over at Andrew Gelman's blog.