Download
brms is an R package by Paul Bürkner which provides a high-level interface for fitting Bayesian multilevel (i.e. mixed effects) models, generalized linear / non-linear / multivariate models using Stan as the backend. It allows R users to specify complex Bayesian models using formula syntax similar to lme4 but with far more flexibility (distributions, link functions, hierarchical structure, nonlinear terms, etc.). It supports model diagnostics, posterior predictive checking, model comparison, custom priors, and advanced features such as distributional regression.
Features
- Supports a very wide range of distributions and link functions: linear, robust linear, count, ordinal, survival, response times, zero-inflated, hurdle, mixture models etc.
- Multilevel / hierarchical models: grouping factors, random effects etc.
- Nonlinear and smooth terms (nonlinear modeling) and autocorrelation / time series structures etcetera
- Flexible prior specification for all parts of the model (including custom priors)
- Model diagnostics and model comparison: posterior predictive checks, leave-one-out cross-validation (LOO), comparison of fits etc.
- Ability to work with user-specified covariance structures, meta-analytic standard errors, censoring/truncation etc.
Project Samples
Categories
Data VisualizationLicense
GNU General Public License version 3.0 (GPLv3)Follow brms
Other Useful Business Software
Build Securely on AWS with Proven Frameworks
Moving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of brms!
