Sensitivity Analysis for Publication Bias in Diagnostic Meta‐Analysis of Sparsity Using the Copas t ‐Statistic Selection Function
Statistics in Medicine · 2026
DOI: 10.1002/sim.70465 ↗At a glance
Journal article in Statistics in Medicine, 2026. Written by Taojun Hu and 3 co-authors. Institution: Department of Biomedical Statistics, Graduate School of Medicine, The University of Osaka, Osaka, Japan. Major MEDLINE topics: Meta-Analysis as Topic, Publication Bias, Models, Statistical. 19 references. The full text is freely available (open access, CC BY 4.0). Funded by: Grant-in-Aid for Scientific Research.
Abstract (original language)
Publication bias (PB) poses a significant threat to meta‐analysis of diagnostic studies, as studies yielding significant results are more likely to be published in scientific journals, leading to the synthesized diagnostic capacity possibly being overestimated. Sensitivity analysis provides a flexible method to address PB by assuming different proportions of unpublished studies. Most existing methods addressing PB in meta‐analysis of diagnostic studies are based on the bivariate normal model using normal approximations. However, they are unsuitable for meta‐analysis with sparse data, which is common in diagnostic studies with high sensitivities or specificities. Alternatively, the bivariate binomial model relies on the exact within‐study model and has better finite sample properties. To address PB in the bivariate binomial model, we model the selective publication process of diagnostic studies by extending the Copas t ‐statistic model and propose the likelihood conditional on published and estimation strategies. Our proposal provides an interpretable way to address PB on the summary receiver operating characteristic curve, an essential tool for synthesizing diagnostic accuracy. We show the practicability of the proposed method on several real‐world meta‐analyses of diagnostic studies and evaluate the performance by simulation studies.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Biomedical Statistics, Graduate School of Medicine, The University of Osaka, Osaka, Japan.
- Department of Biostatistics, School of Public Health, Peking University, Beijing, China.
- Division of Mathematics and Informatics, Graduate School of Human Development and Environment, Kobe University, Kobe, Japan.
- Beijing International Center for Mathematical Research, Peking University, Beijing, China.
- Integrated Frontier Research for Medical Science Division, Institute for Open and Transdisciplinary Research Initiatives (OTRI), The University of Osaka, Osaka, Japan.
ORCID profiles: Taojun Hu, Xiao-Hua Zhou, Satoshi Hattori
Funding
- Grant-in-Aid for Scientific Research
Cite
APA
Hu, T., Zhou, Y., Zhou, X. H., & Hattori, S. (2026). Sensitivity Analysis for Publication Bias in Diagnostic Meta‐Analysis of Sparsity Using the Copas t ‐Statistic Selection Function. Statistics in Medicine. https://doi.org/10.1002/sim.70465
Vancouver
Hu T, Zhou Y, Zhou XH, Hattori S. Sensitivity Analysis for Publication Bias in Diagnostic Meta‐Analysis of Sparsity Using the Copas t ‐Statistic Selection Function. Statistics in Medicine. 2026. doi:10.1002/sim.70465
BibTeX
@article{Hu2026,
author = {Hu, Taojun and Zhou, Yi and Zhou, Xiao-Hua and Hattori, Satoshi},
title = {Sensitivity Analysis for Publication Bias in Diagnostic Meta‐Analysis of Sparsity Using the Copas t ‐Statistic Selection Function},
journal = {Statistics in Medicine},
year = {2026},
doi = {10.1002/sim.70465}
}
EUVIMED