Copas’ method is sensitive to different mechanisms of publication bias

Osama Almalik; Zhuozhao Zhan; Edwin R. van den Heuvel

doi:10.1016/j.spl.2022.109733

Copas’ method is sensitive to different mechanisms of publication bias

Osama Almalik, Zhuozhao Zhan, Edwin R. van den Heuvel (Corresponding author)

Research output: Contribution to journal › Article › Academic › peer-review

1 Citation (Scopus)

72 Downloads (Pure)

Abstract

Copas’ method corrects a pooled estimate from an aggregated data meta-analysis for publication bias. Its performance has been studied for one particular mechanism of publication bias. We show through simulations that Copas’ method is not robust against other realistic mechanisms. This questions the usefulness of Copas’ method, since publication bias mechanisms are typically unknown in practice.

Original language	English
Article number	109733
Number of pages	6
Journal	Statistics and Probability Letters
Volume	194
DOIs	https://doi.org/10.1016/j.spl.2022.109733
Publication status	Published - Mar 2023

Bibliographical note

Funding Information:
This research was funded by the Netherlands Organization for Scientific Research (grant number: 023.005.087 ).

Funding

This research was funded by the Netherlands Organization for Scientific Research (grant number: 023.005.087 ).

Keywords

Copas’ selection model
Meta-analysis
Publication bias

Access to Document

10.1016/j.spl.2022.109733

pdfFinal published version, 647 KBLicence: TAVERNE

Cite this

@article{e6ba9d477c9c4da6a03da8865a8758ee,

title = "Copas{\textquoteright} method is sensitive to different mechanisms of publication bias",

abstract = "Copas{\textquoteright} method corrects a pooled estimate from an aggregated data meta-analysis for publication bias. Its performance has been studied for one particular mechanism of publication bias. We show through simulations that Copas{\textquoteright} method is not robust against other realistic mechanisms. This questions the usefulness of Copas{\textquoteright} method, since publication bias mechanisms are typically unknown in practice.",

keywords = "Copas{\textquoteright} selection model, Meta-analysis, Publication bias",

author = "Osama Almalik and Zhuozhao Zhan and \{van den Heuvel\}, \{Edwin R.\}",

note = "Funding Information: This research was funded by the Netherlands Organization for Scientific Research (grant number: 023.005.087 ). ",

year = "2023",

month = mar,

doi = "10.1016/j.spl.2022.109733",

language = "English",

volume = "194",

journal = "Statistics and Probability Letters",

issn = "0167-7152",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Copas’ method is sensitive to different mechanisms of publication bias

AU - Almalik, Osama

AU - Zhan, Zhuozhao

AU - van den Heuvel, Edwin R.

N1 - Funding Information: This research was funded by the Netherlands Organization for Scientific Research (grant number: 023.005.087 ).

PY - 2023/3

Y1 - 2023/3

N2 - Copas’ method corrects a pooled estimate from an aggregated data meta-analysis for publication bias. Its performance has been studied for one particular mechanism of publication bias. We show through simulations that Copas’ method is not robust against other realistic mechanisms. This questions the usefulness of Copas’ method, since publication bias mechanisms are typically unknown in practice.

AB - Copas’ method corrects a pooled estimate from an aggregated data meta-analysis for publication bias. Its performance has been studied for one particular mechanism of publication bias. We show through simulations that Copas’ method is not robust against other realistic mechanisms. This questions the usefulness of Copas’ method, since publication bias mechanisms are typically unknown in practice.

KW - Copas’ selection model

KW - Meta-analysis

KW - Publication bias

UR - http://www.scopus.com/inward/record.url?scp=85143374984&partnerID=8YFLogxK

U2 - 10.1016/j.spl.2022.109733

DO - 10.1016/j.spl.2022.109733

M3 - Article

AN - SCOPUS:85143374984

SN - 0167-7152

VL - 194

JO - Statistics and Probability Letters

JF - Statistics and Probability Letters

M1 - 109733

ER -

Copas’ method is sensitive to different mechanisms of publication bias

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this