An empirical comparison of heterogeneity variance estimators in 12 894 meta-analyses

2015 ◽  
Vol 6 (2) ◽  
pp. 195-205 ◽  
Author(s):  
Dean Langan ◽  
Julian P. T. Higgins ◽  
Mark Simmonds
Keyword(s):  
Empirical Comparison ◽  
Variance Estimators ◽  
Heterogeneity Variance ◽  
Meta Analyses

scholarly journals A comparison of heterogeneity variance estimators in simulated random‐effects meta‐analyses

2018 ◽  
Vol 10 (1) ◽  
pp. 83-98 ◽  
Author(s):  
Dean Langan ◽  
Julian P.T. Higgins ◽  
Dan Jackson ◽  
Jack Bowden ◽  
Areti Angeliki Veroniki ◽  
...  
Keyword(s):  
Random Effects ◽  
Variance Estimators ◽  
Heterogeneity Variance ◽  
Meta Analyses

scholarly journals Empirical comparison of univariate and multivariate meta‐analyses in Cochrane Pregnancy and Childbirth reviews with multiple binary outcomes

2019 ◽  
Vol 10 (3) ◽  
pp. 440-451
Author(s):  
Malcolm J. Price ◽  
Helen A. Blake ◽  
Sara Kenyon ◽  
Ian R. White ◽  
Dan Jackson ◽  
...  
Keyword(s):  
Binary Outcomes ◽  
Empirical Comparison ◽  
Pregnancy And Childbirth ◽  
Meta Analyses

scholarly journals An empirical comparison of meta-analyses of published gene-disease associations versus consortium analyses

2009 ◽  
Vol 11 (3) ◽  
pp. 153-162 ◽  
Author(s):  
A Cecile J W Janssens ◽  
Angela M González-Zuloeta Ladd ◽  
Sandra López-Léon ◽  
John P A Ioannidis ◽  
Ben A Oostra ◽  
...  
Keyword(s):  
Empirical Comparison ◽  
Disease Associations ◽  
Meta Analyses

A comparison of heterogeneity variance estimators in combining results of studies

2006 ◽  
Vol 26 (9) ◽  
pp. 1964-1981 ◽  
Author(s):  
Kurex Sidik ◽  
Jeffrey N. Jonkman
Keyword(s):  
Variance Estimators ◽  
Heterogeneity Variance

An empirical comparison of univariate and multivariate meta-analyses for categorical outcomes

2013 ◽  
Vol 33 (9) ◽  
pp. 1441-1459 ◽  
Author(s):  
Thomas A. Trikalinos ◽  
David C. Hoaglin ◽  
Christopher H. Schmid
Keyword(s):  
Empirical Comparison ◽  
Meta Analyses

scholarly journals Bayesian Methods for Meta-Analyses of Binary Outcomes: Implementations, Examples, and Impact of Priors

2021 ◽  
Vol 18 (7) ◽  
pp. 3492
Author(s):  
Fahad M. Al Amer ◽  
Christopher G. Thompson ◽  
Lifeng Lin
Keyword(s):  
Bayesian Methods ◽  
Meta Analysis ◽  
Statistical Significance ◽  
Sensitivity Analyses ◽  
Binary Outcomes ◽  
Inverse Gamma ◽  
Log Normal ◽  
Heterogeneity Variance ◽  
Many Sources ◽  
Meta Analyses

Bayesian methods are an important set of tools for performing meta-analyses. They avoid some potentially unrealistic assumptions that are required by conventional frequentist methods. More importantly, meta-analysts can incorporate prior information from many sources, including experts’ opinions and prior meta-analyses. Nevertheless, Bayesian methods are used less frequently than conventional frequentist methods, primarily because of the need for nontrivial statistical coding, while frequentist approaches can be implemented via many user-friendly software packages. This article aims at providing a practical review of implementations for Bayesian meta-analyses with various prior distributions. We present Bayesian methods for meta-analyses with the focus on odds ratio for binary outcomes. We summarize various commonly used prior distribution choices for the between-studies heterogeneity variance, a critical parameter in meta-analyses. They include the inverse-gamma, uniform, and half-normal distributions, as well as evidence-based informative log-normal priors. Five real-world examples are presented to illustrate their performance. We provide all of the statistical code for future use by practitioners. Under certain circumstances, Bayesian methods can produce markedly different results from those by frequentist methods, including a change in decision on statistical significance. When data information is limited, the choice of priors may have a large impact on meta-analytic results, in which case sensitivity analyses are recommended. Moreover, the algorithm for implementing Bayesian analyses may not converge for extremely sparse data; caution is needed in interpreting respective results. As such, convergence should be routinely examined. When select statistical assumptions that are made by conventional frequentist methods are violated, Bayesian methods provide a reliable alternative to perform a meta-analysis.

Sign in / Sign up

Export Citation Format

Share Document