The bmeta package provides a collection of functions for conducting meta-analyses under Bayesian context in R. The package includes functions for computing various effect size or outcome measures (e.g. odds ratios, mean difference and incidence rate ratio) for different types of data based on MCMC simulations. Users are allowed to fit fixed- and random-effects models with different priors to the data. Meta-regression can be carried out if effects of additional covariates are observed. Furthermore, the package provides functions for creating posterior distribution plots and forest plot to display main model output. Traceplots and some other diagnostic plots are also available for assessing model fit and performance.
Bayesian meta-analysis is becoming more frequently accepted as a statistical approach for evidence synthesis from multiple studies in health research. The Bayesian methods differ inherently from frequentist ones by assuming that model parameters are random quantities. Therefore, prior distributions for model parameters can be specified, which are normally based on external evidence. The bmeta function provides 22 models with commonly used priors for fitting different types of data (i.e. binary, continuous and count data).
Tao Ding, Gianluca Baio
Maintainer: Gianluca Baio <[email protected]>
Alex J Sutton and Keith R Abrams.(2001).Bayesian methods in meta-analysis and evidence synthesis. Statistical Methods in Medical Research,10,277-303.
Welton,N.J., Sutton,A.J., Cooper,N., Abrams,K.R.& Ades,A.E.(2012) Evidence synthesis for decision making in healthcare. Chichester, UK: John Wiley & Sons, Ltd.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.