Background about science
In an interview I did with Gary King, he said there wasn’t in reality such a thing as the scientific method. Ask someone in medicine (or economics), they might say the scientific method involves randomization, but if randomization is the core of science, then astronomy isn’t a science. Science, he said, was more generally a set of rules governing communities that harness work activities with rewards and sanctions, and if designed well, the activities are in aggregate able to produce scientific discoveries more often than we could have with any other way of organizing activity.
But what are we to do with theories that make strange predictions other than test them, and if we test them, what else are we to do than use randomized experiments? For as Ronald Fisher noted in his 1925 book, physical randomization can hold the key to identifying aggregate causal parameters. And oftentimes, at least in economics, the predictions of a theory imply “holding all other thi…
Keep reading with a 7-day free trial
Subscribe to Scott's Substack to keep reading this post and get 7 days of free access to the full post archives.