software

(s denotes student)

The output analysis tools developed in various papers are integrated into multiple R packages.

• R package mcmcse. [CRAN] [GitHub devel version]
  Provides tools for computing Monte Carlo standard errors (MCSE) in Markov chain Monte Carlo (MCMC) settings. MCSE computation for expectation and quantile estimators is supported as well as multivariate estimations. The package also provides functions for computing effective sample size and for plotting Monte Carlo estimates versus sample size. Co-developers: James Flegal, John Hughes, Ning Dai, Uttiya Maji^s

• R package stableGR [CRAN] [GitHub devel version]
  A stable Gelman-Rubin diagnostic for Markov chain Monte Carlo. Package uses stable variance estimates to calculate the Gelman-Rubin diagnostic, in addition to smart cut-offs for the diagnostic. The package is built compatible with multiple chain inputs.
  Maintainer and co-developer: Christina Knudson

• R package multichainACF [Webpage][GitHub devel version]
  Plots globally-centered autcorrelation function (ACF) plots following Agarwal and Vats (2020). The functions differ from the base acf and ccf by centering the chains around the global mean from all Markov chains.
  Maintainer and co-developer: Medha Agarwal^s

Other packages for specific models:

• R package qbld [CRAN] [GitHub devel version]
  The R package qbld implements the Bayesian quantile regression model for binary longitudinal data (QBLD) developed in Rahman and Vossmeyer (2019). Supported by Google Summer of Code 2020.
  Maintainer and co-developer: Ayush Agarwal^s