How many of your 80 discoveries are probably fake?
You ran the Benjamini-Hochberg procedure controlling the false discovery rate at , and it flagged 80 signals as significant.
Roughly how many of these 80 discoveries should you expect to be false?
Your answer
Solving needs a free account
Answers, streaks and solutions unlock when you are signed in. Reading the question and the hint stays free.
Discussion
Sign in to join the discussion · reading is open to everyone
💡 Discussion rules
- No full solutions here. Hints and approaches only.
- Complexity, edge cases and intuition are the point.
- Interview experiences are welcome. Respect your NDAs.
Loading discussion…
Learn the concepts
The theory behind this question.
Related questions
Walk the Benjamini-Hochberg ladder for 8 p-valuesBenjamini-Hochberg on 5 p-valuesBenjamini-Hochberg on 10 p-values at q = 0.10BH step-up: a later rung rescues an earlier missWhen Benjamini-Hochberg rejects nothing
All questions →