Statistics & ProbabilityHard

Why do you need multiple-testing correction, and which method do you pick?

Seen at: Meta · Netflix · Uber

Your team runs 20 metrics in an A/B test. One is significant at p=0.04. The PM wants to ship. Walk through why this might be a false alarm and what you'd do.

Draft your answer

Saved to this browser only. Try it before you peek at the model answer.

Reveals the model answer and the self-score rubric.

More statistics & probability questions