<link rel="stylesheet" href="styles.f3b1fba60ec7970c.css">

newway515/adl-cross-national-comparability-audit: v1.0.0 — Frozen Pre-Results Study Protocol

Loading...
Thumbnail Image

Date

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Zenodo

DOI

Abstract

Description

&lt;h2&gt;What this release contains&lt;/h2&gt; &lt;p&gt;This is the &lt;strong&gt;immutable, timestamped, pre-results&lt;/strong&gt; frozen study protocol for:&lt;/p&gt; &lt;p&gt;&lt;strong&gt;&quot;Auditing the Comparability of Cross-National ADL Disability Estimates: A Partial-Identification Decomposition of Item, Scoring, and Differential-Item-Functioning Effects, with an Identifiability-Frontier Map&quot;&lt;/strong&gt;&lt;/p&gt; &lt;p&gt;All analysis decisions (F1–F17, documented in Protocol Appendix C) were frozen before contact with the real-data analysis layer (M2 onwards). This release, combined with its Zenodo DOI timestamp, provides third-party verifiable evidence that these decisions were not made post-hoc.&lt;/p&gt; &lt;h2&gt;Repository contents at v1.0.0&lt;/h2&gt; &lt;ul&gt; &lt;li&gt;&lt;code&gt;protocol/&lt;/code&gt; — Complete V9.1 study protocol (~30 pages, Chinese)&lt;/li&gt; &lt;li&gt;&lt;code&gt;handoff/&lt;/code&gt; — Original V8.1 handoff package including M1 real-data extraction audit (13 populations, N=64,644) and C8 synthetic-data simulation results (12 scenarios × 1000 replications)&lt;/li&gt; &lt;li&gt;&lt;code&gt;reviews/&lt;/code&gt; — Four independent peer reviews of the study design&lt;/li&gt; &lt;li&gt;&lt;code&gt;supplementary/&lt;/code&gt; — Protocol comparison, review-to-revision mapping table, and archived V9.0 drafts&lt;/li&gt; &lt;/ul&gt; &lt;h2&gt;Key empirical constraints (known pre-M2)&lt;/h2&gt; &lt;ol&gt; &lt;li&gt;E1 (item-definition effect) ≈ 0 globally — Gateway harmonization has unified ALL ADL item definitions upstream&lt;/li&gt; &lt;li&gt;E2 (scoring effect) nonzero only in CHARLS — the only cohort retaining a 4-level severity scale&lt;/li&gt; &lt;li&gt;E3 (DIF effect) is the sole substantive source of residual non-comparability — and is NOT point-identifiable with 5 binary items and no anchoring vignettes&lt;/li&gt; &lt;/ol&gt; &lt;h2&gt;Transparency&lt;/h2&gt; &lt;p&gt;This release serves as the pre-results decision freeze. The Zenodo DOI for this release should be cited in the paper's Methods section.&lt;/p&gt;

Keywords

Citation

Collections

Endorsement

Review

Supplemented By

Referenced By

Rights and licensing

info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode