Notes on Thinking
Andrew Gelman says:
Statistics does not require randomness. The three essential elements of statistics are measurement, comparison, and variation. Randomness is one way to supply variation, and it’s one way to model variation, but it’s not necessary. Nor is it necessary to have “true” randomness (of the dice-throwing or urn-sampling variety) in order to have a useful probability model.
Suicide of the Liberals in First Things:
In one memorable scene, the hero of Solzhenitsyn’s novel November 1916, Colonel Vorotyntsev, finds himself at a social gathering principally of Kadet adherents, where everyone repeats the same progressive pieties. He soon grasps that “each of them knew in advance what the others would say, but that it was imperative for them to meet and hear all over again what they collectively knew. They were all overwhelmingly certain that they were right, yet they needed these exchanges to reinforce their certainty.”
