BayesMeta is an R package under active development that will include a wide array of Bayesian meta analysis models.
Overview
Install metapack
Learn how to install metapack package and see how to troubleshoot potential errors.
bayes.nmr
bayes.nmr is a function that fits the model introduced in Bayesian Network Meta-Regression Models Using Heavy-Tailed Multivariate Random Effects with Covariate-Dependent Variances (submitted). This page serves as a self-contained tutorial for bayes.
bayes.parobs
bayes.parobs is the function is based on Yao, H., Kim, S., Chen, M. H., Ibrahim, J. G., Shah, A. K., & Lin, J. (2015). Bayesian inference for multivariate meta-regression with a partially observed within-study sample covariance matrix.
Numerical Methods
Localized Metropolis Algorithm The efficiency of a Markov chain Monte Carlo (MCMC) algorithm depends on a few factors: the calculation of the objective function, or the logarithm of the joint likelihood, and the quality of the proposal distribution.
Model Assessment and Treatment Ranking
Once the posterior sampling is done, metapack provides graphical tools to assess the model. Currently, a function for the surface under the cumulative ranking (SUCRA) plot is included. Model selection tools like the deviance information criterion (DIC) and log pseudo-marginal likelihood (LPML) are also available.