A recent news story was about doctors not knowing the basics of Bayes’ theorem: they were asked a basic question about false results on a disease test. A lot of them flubbed it.

Let’s be fair: I wouldn’t expect most doctors to be able to regurgitate Bayes law or do an applied example.

I would expect them to say “That question is more complex than it sounds”, rather than fall into the usual trap.

It’s the old knowing what you don’t know (and that’s for another post).

Anyway, that was the prod for me do a dive into basics of Bayesian Analysis in several parts.

Introducing the simplex generator for higher dimension pascal/combinatorics and looking at the bigger picture: exhaustive function composition.

This is the first of a few notes about combinatorics and probability. Simpler concepts first, and eventually might get to stuff like analytic combinatorics.

I’m interested in the point where more simple combinatorics and multinomials become blunt tools and we have to move to higher concepts like generators and species.