Tidybayes supports two classes of models and sample formats: Models that provide prediction functions, and those that do not.
All supported models support the base tidybayes sample extraction functions, such as
as_sample_tibble, spread_samples, and gather_samples. These models include:
rstan models
brm models
rstanarm models
runjags models
jags.model models, if sampled using coda.samples
jags models
MCMCglmm models
mcmc and mcmc.list objects, which are output by several model
types.
Any object with an implementation of as.mcmc.list. For a list of those available in your
environment, run methods(as.mcmc.list)
If you install the tidybayes.rethinking package (available at
https://github.com/mjskay/tidybayes.rethinking), map and
map2stan models from the rethinking package are also supported.
In addition, the following models support fit and prediction extraction functions, such as
add_fitted_samples and add_predicted_samples:
If you install the tidybayes.rethinking package, models from
the rethinking package are also supported. Note that in
tidybayes.rethinking, tidy_link takes the place of
add_fitted_samples and tidy_sim takes the place of
add_predicted_samples.
To include basic support for new models, one need only implement the as_sample_tibble generic function
for that model.
To include support for estimation and prediction, one must implement the fitted_samples and
predicted_samples generic functions.