Metraipolis › archive › dc_ede5e7604b13

How Wrong Can a Rank-Based Sample-Size Calculation Be? A Sharp Bound of 16/9 for Ordinal Outcomes — arXiv:2609.06575

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.06575
License (as archived)
CC0-1.0
Archived
2026-10-16T14:09:42.231Z
SHA-256 of the archived text
33f728db378af76e85e62a53eac5ed978122d44854f4adfc143d2ac1a5b05e33
Stable URL of this page
https://metraipolis.com/documento/dc_ede5e7604b13

How to cite

How Wrong Can a Rank-Based Sample-Size Calculation Be? A Sharp Bound of 16/9 for Ordinal Outcomes — arXiv:2609.06575 — arXiv (en), https://arxiv.org/abs/2609.06575 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ede5e7604b13 (Metraipolis archive dc_ede5e7604b13, sha256 33f728db378af76e85e62a53eac5ed978122d44854f4adfc143d2ac1a5b05e33)
BibTeX
@misc{dcede5e7604b13,
  title = {How Wrong Can a Rank-Based Sample-Size Calculation Be? A Sharp Bound of 16/9 for Ordinal Outcomes — arXiv:2609.06575},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.06575},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ede5e7604b13; sha256 33f728db378af76e85e62a53eac5ed978122d44854f4adfc143d2ac1a5b05e33},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06575. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Rank-based tests need no distributional assumptions to be valid, but the sample size they require does depend on the shapes of the two outcome distributions, which are unknown at the design stage. Standard practice substitutes a variance calibrated under the null. We ask how wrong that substitution can be. Writing $\Pi$ for the ratio of the true asymptotic variance of the estimated relative effect to the substituted one, we prove that under balanced allocation $\Pi \le 16\theta(1-\theta)/\{2+\theta(1-\theta)\} \le 16/9$ for all ordinal distributions in any number of categories: within the first-order asymptotic calculation the required sample size can exceed the calculated one by at most $77.8\%$, and an explicit two-point family attains the bound at every effect size. The effect-specific envelope, not the constant, is the operative quantity for a design: the ceiling falls to $1.63$ at $\theta=0.65$ and $1.37$ at $\theta=0.75$, so a trial powered for a larger effect is correspondingly less exposed. The proof is elementary. In five extracted trial comparisons and 4,711 generated alternatives the realized cost stays within a few percent, because the extremal configuration is one that shift-type treatment mechanisms do not produce. These facts are complementary, and fix how the bound should be used: it is a design sensitivity certificate, not an inflation factor. A protocol can report the conventional sample size alongside the largest requirement consistent with any ordinal configuration.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in stat.ME).
Categorie arXiv: Methodology (stat.ME).
Pagina del lavoro: https://arxiv.org/abs/2609.06575 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T13:59:27.856Z dalla pagina https://arxiv.org/catchup/stat.ME/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).