Lesson 1 · Statistical Inference · Step 5 of 5
The Bayesian approach
A positive rapid COVID test means something different in a quiet month than in a surge, and the difference is the base rate you started from. Bayesian inference makes that explicit: a prior, what you believed beforehand; the data; and a posterior, what you believe now. Its credible interval says what people wrongly think a confidence interval says — a 95% probability the value lies in this range. Analysed both ways, the same trial often yields nearly identical numbers. What differs is what you are entitled to say about them.
Also covered: priors and posteriors · credible intervals · base rates · Bayes' rule
Alongside this step
- Slides and transcript — the whole video
- Read the chapter — Statistical Inference
Check yourself
5 questions, marked as you go. Nothing is recorded as a grade and nothing is locked behind it — if a question catches you out, that is the useful part.
Lesson 1 · 5 steps
The Validity Toolkit · lesson 1 of 4