The Math Beneath · Part 4 / 8

Where the walk starts

A 99%-accurate test says you have a rare disease — and you're probably fine. Paradox on the probability ruler, plain addition on the straight one. Bayes' rule is chapter three plus a starting point.

A screening test for a rare condition is 99% accurate. Yours comes back positive. How worried should you be?

Nearly everyone — doctors included, in study after study — says something like “99%”. The real answer, for a condition affecting 1 in 1,000 people, is about 9%. Told this on the probability ruler, it sounds like a trick. On the straight ruler, it’s one line of arithmetic.

Evidence is a step. The prior is where you’re standing.

Chapter three established what a clue is worth: the test’s evidence is how much more often it says positive on the sick than on the healthy — it catches 99% of real cases and false-alarms on 1% of healthy people, so a positive multiplies your odds by 99. On the log ruler: +4.6 points. That part everyone feels.

Here’s the forgotten half. Before the test, you weren’t at 50/50. The condition is 1-in-1,000 rare, so you started at odds of 1:999 — about −6.9 points, deep in “almost certainly not.” That starting position is the prior, and it is not optional; standing somewhere is not a choice you can decline.

Now the whole of Bayes’ rule, as lived on the straight ruler:

posterior = prior + evidence = −6.9 + 4.6 = −2.3 → sigmoid → 9%

The test was genuinely strong — +4.6 points is a big stride. But you started 6.9 points below zero. One big stride from deep in the hole still leaves you in the hole. The “paradox” was never about the test; it was about forgetting where the walk starts.

Try it: guess before you reveal — the gap between your instinct and the answer is this chapter. Then hit take the test twice: a second positive adds another +4.6, and now you’re at +2.3 → 91%. Evidence stacks by addition, exactly as chapter three promised.

Believing is arithmetic

Read the update rule once more, because it’s the whole machinery of rational belief in five words: start honest, add the evidence.

• A weak prior and strong evidence → evidence wins. (Coin-flip prior + one positive test → 99%.)
• A strong prior and one clue → the prior barely budges. (1-in-100,000 + one positive → still only ~0.1%.)
• More evidence → more addition. Nothing else changes.

The prior is where you stand; evidence is how you step. Next: what you can say about a future you can’t see at all — averages over randomness.