2019
DOI: 10.31219/osf.io/p3xyd
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Estimating publication bias in meta-analyses of peer-reviewed studies: A meta-meta-analysis across disciplines and journal tiers

Abstract: Selective publication and reporting in individual papers compromise the scientific record, but are meta-analyses as compromised as their constituent studies? We systematically sampled 63 moderately large meta-analyses (at least 40 studies per meta-analysis) in PLOS One, top medical journals, top psychology journals, and Metalab, an online, open-data database of devel- opmental psychology meta-analyses. We empirically estimated publication bias in each. Across all meta-analyses, “statistically significant” re… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4

Citation Types

1
26
0

Year Published

2019
2019
2022
2022

Publication Types

Select...
5
2

Relationship

2
5

Authors

Journals

citations
Cited by 17 publications
(27 citation statements)
references
References 14 publications
1
26
0
Order By: Relevance
“…If so, publication bias might have been relatively mild in meta-analyses because, in principle, highquality meta-analyses include all studies published in any journal and at any time, so even if elite journals and nascent fields induce severe publication bias by excluding nearly all nonaffirmative results, it is possible that these nonaffirmative results are still eventually published, perhaps in a lower-tier journals, and hence are still included in the meta-analysis. However, additional analyses did not support these hypotheses (Mathur & VanderWeele, 2020a). Instead, preliminary evidence suggested that the key alleviator of publication bias in the meta-analyses may have been their inclusion of "non-headline" results; that is, results that are reported in published papers but that are de-emphasized (e.g., those reported only in secondary or supplemental analyses) and those that meta-analysts obtain through manual calculation or by contacting authors (Mathur & VanderWeele, 2020a).…”
Section: Empirical Benchmarks For Interpreting S(t Q)mentioning
confidence: 96%
See 3 more Smart Citations
“…If so, publication bias might have been relatively mild in meta-analyses because, in principle, highquality meta-analyses include all studies published in any journal and at any time, so even if elite journals and nascent fields induce severe publication bias by excluding nearly all nonaffirmative results, it is possible that these nonaffirmative results are still eventually published, perhaps in a lower-tier journals, and hence are still included in the meta-analysis. However, additional analyses did not support these hypotheses (Mathur & VanderWeele, 2020a). Instead, preliminary evidence suggested that the key alleviator of publication bias in the meta-analyses may have been their inclusion of "non-headline" results; that is, results that are reported in published papers but that are de-emphasized (e.g., those reported only in secondary or supplemental analyses) and those that meta-analysts obtain through manual calculation or by contacting authors (Mathur & VanderWeele, 2020a).…”
Section: Empirical Benchmarks For Interpreting S(t Q)mentioning
confidence: 96%
“…However, additional analyses did not support these hypotheses (Mathur & VanderWeele, 2020a). Instead, preliminary evidence suggested that the key alleviator of publication bias in the meta-analyses may have been their inclusion of "non-headline" results; that is, results that are reported in published papers but that are de-emphasized (e.g., those reported only in secondary or supplemental analyses) and those that meta-analysts obtain through manual calculation or by contacting authors (Mathur & VanderWeele, 2020a).…”
Section: Empirical Benchmarks For Interpreting S(t Q)mentioning
confidence: 96%
See 2 more Smart Citations
“…For more general set of recommendations on how to conduct a rigorous meta-analysis, see a comprehensive guidance paper by Pigott & Polanin (2019). 9 When (1) conducting a prospective or mini meta-analysis and synthesizing (2) a set of studies conducted as registered reports or (3) "non-headline" effects, i.e., effects independent from the focal effect of the paper(Mathur & VanderWeele, 2019b).10 In some analytical contexts, the goal may be just to summarize the results of a finite set of studies without attempting to draw generalizable inferences about unobserved studies (using fixed-effects meta-analytic models).…”
mentioning
confidence: 99%