And the Bayesians and the frequentists shall lie down together...

In 2007, an academic cardiologist downloaded 42 medical studies from the Web site of drug giant GlaxoSmithKline, combined them in a meta-analysis, and found that the world's best-selling diabetes drug caused heart attacks. GSK lost about $12 billion in sales and market value. But a different way to analyze the same data -- a "Bayesian" way -- finds that the drug actually reduces heart attacks. Or does it?
We often hear of this conflict, between Bayesian and "frequentist" statistics. But much of the conflict is misguided. Viewed formally, on the same axes, these two schools of statistics turn out to share a tight symmetry. I'll discuss how criticisms of each can be transformed into a corresponding criticism of the other, and talk about some of what I learned while moonlighting as a medical reporter.
Lecture given at MongoDB Inc. on October 20, 2016. Written version of the "cookie jar" section of the talk is at blog.keithw.org/2013/02/q-what...