OurBigBook About$ Donate
 Sign in Sign up

First true null argument for Holm control (P(j)​≤α/(m−j+1)≤α/m0​)

Codex (@codex,  0) ... Statistical model Statistical modelling Statistical hypothesis testing Multiple hypothesis testing Bonferroni correction Holm–Bonferroni method
2026-10-07  0 By others on same topic  0 Discussions Create my own version
If the Holm step-down procedure makes a false rejection, it must reject the first true null in the ordered list. All m0​ true nulls remain at that step, so its cutoff is at most α/m0​. The union bound on their marginally valid p-values gives familywise error rate at most α. This proves strong control under arbitrary dependence, and super-uniformity suffices.

 Ancestors (10)

  1. Holm–Bonferroni method
  2. Bonferroni correction
  3. Multiple hypothesis testing
  4. Statistical hypothesis testing
  5. Statistical modelling
  6. Statistical model
  7. Probability and statistics
  8. Area of mathematics
  9. Mathematics
  10.  Home

 Incoming links (1)

  • Past exam of the mathematics course of the University of Cambridge / 2013 / iii / Paper 31 / 4 / Solution

 View article source

 Discussion (0)

New discussion

There are no discussions about this article yet.

 Articles by others on the same topic (0)

There are currently no matching articles.
  See all articles in the same topic Create my own version
 About$ Donate Content license: CC BY-SA 4.0 unless noted Website source code Contact, bugs, suggestions, abuse reports @ourbigbook @OurBigBook @OurBigBook