Shortcomings of an approximate confidence interval for moment-based estimators of the between-study variance in random-effects meta-analysis.

@article{Hoaglin2016ShortcomingsOA,
  title={Shortcomings of an approximate confidence interval for moment-based estimators of the between-study variance in random-effects meta-analysis.},
  author={David C. Hoaglin},
  journal={Research synthesis methods},
  year={2016},
  volume={7 4},
  pages={459-461}
}
Jackson et al. (2015) present moment-based approximate confidence intervals (CIs) for the between-study variance, τ, in random-effects meta-analysis. In the context of meta-regression, their model is Yi xi ∼N xi β; σi þ τ ; where Yi is the estimated effect from Study i (i= 1, 2,..., n), xi is the 1 × p vector of covariates associated with Study i, β is the corresponding vector of regression coefficients, σi is the within-study variance of Yi, and τ 2 is the between-study variance (in a meta… CONTINUE READING