[R-sig-ME] Release of the R package brms to fit Bayesian mixed effects models

Paul Buerkner paul.buerkner at gmail.com
Thu May 28 11:44:27 CEST 2015


Hi all,

I just wanted to inform you about the release of a new R package for
fitting bayesian mixed effects models.

The package is called *brms* (Bayesian Regression Models using Stan) and is
based on the probabilistic programming language Stan (see
http://mc-stan.org/).

A wide range of families is supported, also including families for survival
regression such as "weibull" or ordinal regression such as "cumulative"
besides the standard families "gaussian", "poisson", "binomial", etc. The
formula syntax is basically that of lme4.

brms itself is available on CRAN. Unfortunately, the package rstan
(implementing Stan in R) is not on CRAN yet, so it has to be installed
manually before brms can be used to fit the models. For instructions on how
to install rstan please see
https://github.com/stan-dev/rstan/wiki/RStan-Getting-Started

I am very grateful for every feedback regarding brms! If you have any
questions, please contact me.

Best
Paul

	[[alternative HTML version deleted]]



More information about the R-sig-mixed-models mailing list