Field note · March 23, 2024
Reader question — Correlation, confounding, and Simpson's paradox
The gap between "these move together" and "this causes that" is where most bad decisions live. Here is how to see the gap, and what to do when you cannot close it.
Reader question on Correlation, confounding, and Simpson's paradox, and the answer belongs somewhere more findable than an email.
The gap between "these move together" and "this causes that" is where most bad decisions live. Here is how to see the gap, and what to do when you cannot close it.
The question was, roughly, "when does this stop applying?" — which is the right question and the one lessons routinely fail to answer. Every technique has a range of validity, and stating it is what separates a lesson from a recipe.
It sits in the Statistics you will actually use module, and the exercise runs against world-indicators. That pairing is deliberate: the dataset was built with the trap the lesson describes already in it, so the exercise fails in the instructive way rather than the confusing one.
Ordering matters here more than in most courses. It follows The five tests that cover most questions and leads into Designing an experiment that can succeed, and reading it out of sequence mostly works but costs you the setup.
Free means free, and it also means we can rewrite it whenever it is wrong. No edition, no errata PDF, nothing to repurchase. The whole course is 36 lessons and the fixes land the day we find them.