Not published is not perished : Addressing publication bias in meta-analytic studies in communication

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

8 Scopus Citations
View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Pages (from-to)300-321
Journal / PublicationHuman Communication Research
Volume46
Issue number2-3
Online published4 Mar 2020
Publication statusPublished - Apr 2020
Externally publishedYes

Abstract

Publication bias has been recognized as a threat to the validity of meta-analytic findings and scientific knowledge in general. Given the recent rise in meta-analytic research in communication, how well publication bias concerns are addressed by communication meta-analysts merits attention. In this essay, after a brief overview of publication bias and some major methods of assessment, we provide a systematic review of meta-analyses published in six major communication journals between 2005 and 2018. The review focuses on two aspects of addressing publication bias in meta-analyses: (a) reducing the potential impact of bias via an inclusive literature search; and (b) empirically assessing the extent and impact of bias in meta-analytic findings. Our review shows that the current practices in communication meta-analyses are inadequate in both aspects. We offer recommendations on ways of improving practices in meta-analyses, as well as in research and publication processes, to better safeguard knowledge claims.

Research Area(s)

  • Meta-Analysis, Meta-Research, Publication Bias, Questionable Research Practices (QRPs), Sensitivity Analysis