What question did this study set out to answer?

September 2, 2015Research Synthesis MethodsOpen Access

Methods to estimate the between‐study variance and its uncertainty in meta‐analysis

View Full Paper

Ask AI

Bookmark

Authors

AVAreti Angeliki VeronikiRhode Island Department of Health DJDan JacksonAstraZeneca (United Kingdom)WVWolfgang ViechtbauerMaastricht University

Discussion

Member takes

Implication

Methodological review reveals superior alternatives to standard variance estimators in meta-analyses, indicating that Paule-Mandel and restricted maximum likelihood improve statistical accuracy.

Key Points

To identify available methods for estimating between-study variance and its uncertainty in meta-analyses and synthesize evidence comparing their performance.
Identified and reviewed 16 between-study variance estimators and seven confidence interval calculation methods from published empirical and simulation studies.
Synthesized comparative performance data through a qualitative evaluation of the literature supported by expert consensus.
Simulation evidence showed that the Paule and Mandel estimator for dichotomous and continuous data, alongside restricted maximum likelihood for continuous data, outperformed the standard DerSimonian and Laird method.
The Q-profile approach and the generalized Cochran between-study variance statistic were recommended as the most reliable methods for deriving confidence intervals around variance estimates.

Cite This Study

Veroniki et al. (2015) studied this question.

synapsesocial.com/papers/69990ae5fcab04efb4ebbc9b https://doi.org/10.1002/jrsm.1164

View Full Paper

Ask AI

Bookmark

Implication

Methodological review reveals superior alternatives to standard variance estimators in meta-analyses, indicating that Paule-Mandel and restricted maximum likelihood improve statistical accuracy.

Methods to estimate the between‐study variance and its uncertainty in meta‐analysis

Discussion

Member takes

Implication

Key Points

Cite This Study

Methods to estimate the between‐study variance and its uncertainty in meta‐analysis

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider