Arcsine‐based transformations for meta‐analysis of proportions: Pros, cons, and alternatives
Abstract Meta‐analyses have been increasingly used to synthesize proportions (eg, disease prevalence) from multiple studies in recent years. Arcsine‐based transformations, especially the Freeman–Tukey double‐arcsine transformation, are popular tools for stabilizing the variance of each study's...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2020-09-01
|
Series: | Health Science Reports |
Subjects: | |
Online Access: | https://doi.org/10.1002/hsr2.178 |
id |
doaj-e23a4441d2814af1a2b7a77c9f384722 |
---|---|
record_format |
Article |
spelling |
doaj-e23a4441d2814af1a2b7a77c9f3847222021-05-02T06:22:35ZengWileyHealth Science Reports2398-88352020-09-0133n/an/a10.1002/hsr2.178Arcsine‐based transformations for meta‐analysis of proportions: Pros, cons, and alternativesLifeng Lin0Chang Xu1Department of Statistics Florida State University Tallahassee FloridaDepartment of Population Medicine College of Medicine, Qatar University Doha QatarAbstract Meta‐analyses have been increasingly used to synthesize proportions (eg, disease prevalence) from multiple studies in recent years. Arcsine‐based transformations, especially the Freeman–Tukey double‐arcsine transformation, are popular tools for stabilizing the variance of each study's proportion in two‐step meta‐analysis methods. Although they offer some benefits over the conventional logit transformation, they also suffer from several important limitations (eg, lack of interpretability) and may lead to misleading conclusions. Generalized linear mixed models and Bayesian models are intuitive one‐step alternative approaches, and can be readily implemented via many software programs. This article explains various pros and cons of the arcsine‐based transformations, and discusses the alternatives that may be generally superior to the currently popular practice.https://doi.org/10.1002/hsr2.178arcsine‐based transformationBayesian modelgeneralized linear mixed modelmeta‐analysisproportion |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Lifeng Lin Chang Xu |
spellingShingle |
Lifeng Lin Chang Xu Arcsine‐based transformations for meta‐analysis of proportions: Pros, cons, and alternatives Health Science Reports arcsine‐based transformation Bayesian model generalized linear mixed model meta‐analysis proportion |
author_facet |
Lifeng Lin Chang Xu |
author_sort |
Lifeng Lin |
title |
Arcsine‐based transformations for meta‐analysis of proportions: Pros, cons, and alternatives |
title_short |
Arcsine‐based transformations for meta‐analysis of proportions: Pros, cons, and alternatives |
title_full |
Arcsine‐based transformations for meta‐analysis of proportions: Pros, cons, and alternatives |
title_fullStr |
Arcsine‐based transformations for meta‐analysis of proportions: Pros, cons, and alternatives |
title_full_unstemmed |
Arcsine‐based transformations for meta‐analysis of proportions: Pros, cons, and alternatives |
title_sort |
arcsine‐based transformations for meta‐analysis of proportions: pros, cons, and alternatives |
publisher |
Wiley |
series |
Health Science Reports |
issn |
2398-8835 |
publishDate |
2020-09-01 |
description |
Abstract Meta‐analyses have been increasingly used to synthesize proportions (eg, disease prevalence) from multiple studies in recent years. Arcsine‐based transformations, especially the Freeman–Tukey double‐arcsine transformation, are popular tools for stabilizing the variance of each study's proportion in two‐step meta‐analysis methods. Although they offer some benefits over the conventional logit transformation, they also suffer from several important limitations (eg, lack of interpretability) and may lead to misleading conclusions. Generalized linear mixed models and Bayesian models are intuitive one‐step alternative approaches, and can be readily implemented via many software programs. This article explains various pros and cons of the arcsine‐based transformations, and discusses the alternatives that may be generally superior to the currently popular practice. |
topic |
arcsine‐based transformation Bayesian model generalized linear mixed model meta‐analysis proportion |
url |
https://doi.org/10.1002/hsr2.178 |
work_keys_str_mv |
AT lifenglin arcsinebasedtransformationsformetaanalysisofproportionsprosconsandalternatives AT changxu arcsinebasedtransformationsformetaanalysisofproportionsprosconsandalternatives |
_version_ |
1721494485579333632 |