Bayesian Distributional Non-Linear Multilevel Modeling with the R Package brms

The brms package allows R users to easily specify a wide range of Bayesian multilevel models, which are fitted with the probabilistic programming language Stan behind the scenes. A wide range of response distributions are supported in combination with an intuitive and powerful multilevel formula syntax. Non-linear relationships may be specified using non-linear predictor terms, splines or Gaussian processes. Additionally, all parameters of the response distribution can be predicted at the same time allowing for distributional regression. Model fit can be investigated and compared using leave-one-out cross-validation and graphical posterior-predictive checks. Many more post-processing and plotting methods are implemented.