CoChat
Sign Up
Cited by 31Meta-analysis and systematic reviewsStatistical Methods in Clinical TrialsAdvanced Causal Inference Techniques

Justification and reporting of subgroup analyses were lacking or inadequate in randomized controlled trials

Open access
Fan, Jingchun, Song, Fujian, Bachmann, Max O.·2019·Journal of Clinical Epidemiology
DOI 10.1016/j.jclinepi.2018.12.009
Open this paper in CoChat — free accountOpen PDF

Abstract

OBJECTIVES: The aim of the article was to assess the appropriateness and rationales of subgroup analyses planned in protocols of randomized controlled trials and reported in subsequent corresponding trial publications. STUDY DESIGN AND SETTING: We searched PubMed to identify trial protocols published in journals during 2006-2017. From a total of 3,774 initially identified records, we included a random sample of 479 protocols and identified 280 trial publications corresponding to the included protocols. RESULTS: Subgroup analyses were specified in 19% of the protocols and reported in 21% of the trial publications. Of the 94 protocols with planned subgroup analyses, 32% mentioned testing for interaction, and only three considered statistical power. Subgroup analyses were not prespecified in 56% of the 59 trial publications with subgroup analyses. Subgroup analyses were stated as prespecified in nine trial publications, without support evidence from the corresponding protocols. Subgroup analyses were often reported insufficiently for assessing the consistency of subgroup effects across studies. Justifications for subgroup analyses were provided in only four trial protocols and seven trial publications. CONCLUSION: Inappropriate specification and reporting of subgroup analyses remain problematic in protocols and reports of randomized controlled trials. Justifications or rationales for subgroup analyses were only rarely provided in trial protocols and reports.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.jclinepi.2018.12.009

Cites

32 of 32 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Reviews have found that for more than half of trials the subgroup analyses reported in publications do not match those described in protocols.

    “Reviews have found that for more than half of trials the subgroup analyses reported in publications do not match those described in protocols,64 440 raising concerns about post hoc analyses and selective reporting.”

    From SPIRIT 2025 explanation and elaboration: updated guideline for protocols of randomised trials (2025) · cites this paper as [440]

  • Subgroup analyses are highly susceptible to bias and misinterpretation, particularly if they are inappropriately conducted or selectively reported.

    “Although commonly performed,439 440 subgroup analyses are highly susceptible to bias and misinterpretation, particularly if they are inappropriately conducted or selectively reported.”

    From SPIRIT 2025 explanation and elaboration: updated guideline for protocols of randomised trials (2025) · cites this paper as [440]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Related

Authors
Fan, J., Song, F., & Bachmann, M. O.
Affiliations
University of East Anglia (GB)
Corresponding author
Song, Fujian
ORCID
Venue
Journal of Clinical Epidemiology
Publisher
Elsevier BV
Published
2019-04
Volume
108
Pages
17-25
ISSN
0895-4356 (ISSN-L)
DOI
10.1016/j.jclinepi.2018.12.009
OpenAlex
W2904368649
Cited by
31
References
32
Citations by year
2026: 2 · 2025: 2 · 2024: 3 · 2023: 4 · 2022: 5 · 2021: 3 · 2020: 9 · 2019: 3
FWCI
2.86
Type
journal article
Language
en
Open access
Licence
Locations
  • Journal of Clinical Epidemiology (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • UEA Digital Repository (University of East Anglia) (submittedVersion)
Funders
China Scholarship Council (201608625033)
Topics
  • Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
  • Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Clinical Trials
  • Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
Keywords
subgroup analysis, randomized controlled trials, reporting quality, interaction testing, statistical power, treatment effect heterogeneity
MeSH terms
Data Interpretation, Statistical, Humans, Publications, Randomized Controlled Trials as Topic

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review