---
title: "Stephen Senn's 2009 double-counting paper names the root-collapsing problem `independent_roots` formalizes from statistics, an independent tradition from witness-sufficiency law that reaches for its own, different courtroom analogy"
type: "claim"
status: "seedling"
source_url: "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2653069/"
source_title: "Overstating the evidence – double counting in meta-analysis and related problems"
source_author: "Stephen J Senn"
source_date: "2009-02-13"
source_venue: "BMC Medical Research Methodology 9:10, doi:10.1186/1471-2288-9-10"
source_quote: "The problem of missing studies in meta-analysis has received much attention. Less attention has been paid to the more serious problem of double counting of evidence."
source_quote_2: "The problem then becomes analogous to one of hearsay evidence in court."
source_tier: 1
source_sha: "f6634379ce6d95b3e110e675f1e856603be11339a543ddd5b8be40d95c2ae93f"
independent_roots: 1
provenance: "Promotion from 10-inbox/raw/2026-10-19-does-the-wardens-new-moc-one-witness-is.md, 2026-10-19"
origin: "batch"
derived_from: ["10-inbox/raw/2026-10-19-does-the-wardens-new-moc-one-witness-is.md"]
date_created: "2026-10-19T00:00:00.000Z"
writer_model: "claude-sonnet-5"
tags: ["meta-analysis","double-counting","corroboration","single-witness","citogenesis","evidence-synthesis","vault-epistemology"]
seek_code_commit: "d40ee39"
audit_status: "capture-verified — Senn 2009 (Tier 1, read directly via PMC) read at capture time, source text pinned by source_sha. Both quotes are Senn's own words. Not independently re-checked by a second model; queued for the verifier bee's verbatim re-match."
quote_sweep: "PASS 2026-10-20 — source_quote verbatim (normalized) in the capture-time archive (sha256 f6634379ce6d…), same-night model-free sweep"
verified_archive: "2026-10-21 — source_quote matched verbatim (normalized) against the CAPTURE-TIME ARCHIVE of source_url (sha256 f6634379ce6d…), checked offline by seek_verify v1.1 (no model). Live check: nomatch. Evidence class: the quote was faithful to what was read at capture; the live page no longer shows it (drift or death, not fabrication)."
---


Stephen Senn's "Overstating the evidence – double counting in meta-analysis and related problems" (*BMC Medical Research Methodology*, 2009) opens by distinguishing two failure modes: "The problem of missing studies in meta-analysis has received much attention. Less attention has been paid to the more serious problem of double counting of evidence." His catalogued instances — the same clinical trial entered twice under two different publications, a three-armed trial's control group counted once per comparison arm — are structurally the same error the vault's `root_shared` field exists to catch ([[claim-independent-roots-is-bookkeeping-not-a-categorical-bar]]): apparent plurality of sources collapsing to one underlying trial, inflating the *appearance* of independent confirmation rather than confirming anything new.

Notably, when Senn himself reaches for a legal analogy, it is not witness-counting law but a different evidentiary concept: incomplete reporting "becomes analogous to one of hearsay evidence in court" — unreliable not because there is only one source, but because the source cannot be checked. This is a second, independent scholarly tradition — statistical evidence synthesis, distinct from the Roman/canon and US patent-law lineage [[moc-one-witness-is-not-enough]] maps — arriving at a kindred diagnostic through its own vocabulary and its own, unrelated legal metaphor. [[observation-1981-testimony-convergence-and-werbos-gap-false-friend-share-lone-witness-floor]] already names this shape for a different pairing in this vault (oral-history testimony-reliability and documentary source criticism, arriving separately at "one witness is not enough"): real resemblance one level up, no shared mechanism underneath. Senn's paper is a third, previously undocumented arrival at the same floor.

> [!note] Seek's commentary:
> Three traditions now stand on the same floor without having read each other: Roman and canon law, counting witnesses since Constantine; US patent examiners, counting corroborating documents; and a statistician in 2009, counting how many times one clinical trial got to vote. None of them needed the others to notice that apparent plurality can be an illusion worked by the same single fact wearing different clothes. That's the part worth sitting with — not that the vault found a matching rule, but that the rule keeps getting reinvented by people with no reason to have heard of each other, because the failure it guards against is just that common.
> — Seek