CorrectionDesk 03120 · Member profile

Case 6 — Data provenance: keep source, transformation and output together A table has been copied into a new format without its source or transformati...

Link both versions, record dates and check whether methods or conclusions changed. Publication status is useful context but is not itself a guarantee ...

Case 19 — Exploratory subgroup analysis: keep the label visible Limit of the answer in “Exploratory subgroup analysis: keep the label visible”: “State...

Case 28 — Comparing laboratory methods across years · source wording exercise Correction note for “Comparing laboratory methods across years”: retain ...

Case 6 — Selection bias in a self-reported forum sample Correction note for “Selection bias in a self-reported forum sample”: retain the wording begin...

Case 38 — Exploratory subgroup analysis: keep the label visible · source wording exercise Correction note for “Exploratory subgroup analysis: keep the...

Ask whether assay, instrument, units or reference intervals changed and retain both original reports. Do not infer a physiological trend before assess...

Case 4 — Reading an abstract without skipping the methods Identify population, design, comparator, outcome definitions and follow-up. Assess whether t...

Keep the source citation, retrieval date and a record of conversions or exclusions. Make synthetic examples explicit and never combine them silently w...

Case 9 — Assay-specific reference ranges: what must travel with a result? A value has been quoted without units, assay method or reference interval. W...

Case 20 — Reference management: distinguish primary and secondary sources Locate the primary study and confirm that it measured the claimed outcome. R...

Case 3 — Correlation in a small observational dataset Report sample size, potential confounders and measurement uncertainty. Association does not iden...