chkpt_brms | R Documentation |
Fit Bayesian generalized (non-)linear multivariate multilevel models using brms with checkpointing.
chkpt_brms( formula, data, iter_warmup = 1000, iter_sampling = 1000, iter_per_chkpt = 100, iter_typical = 150, parallel_chains = 2, threads_per = 1, chkpt_progress = TRUE, control = NULL, brmsfit = TRUE, seed = 1, path, ... )
formula |
An object of class |
data |
An object of class |
iter_warmup |
(positive integer) The number of warmup iterations to run per chain (defaults to 1000). |
iter_sampling |
(positive integer) The number of post-warmup iterations to run per chain (defaults to 1000). |
iter_per_chkpt |
(positive integer). The number of iterations per
checkpoint. Note that |
iter_typical |
(positive integer) The number of iterations in the
initial warmup, which finds the so-called typical set.
This is an initial phase, and not included in
|
parallel_chains |
(positive integer) The maximum number of MCMC
chains to run in parallel. If parallel_chains is not
specified then the default is to look for the option
|
threads_per |
(positive integer) Number of threads to use in within-chain
parallelization (defaults to |
chkpt_progress |
logical. Should the |
control |
A named list of parameters to control the sampler's behavior.
It defaults to NULL so all the default values are used.
For a comprehensive overview see |
brmsfit |
Logical. Should a |
seed |
(positive integer). The seed for random number generation to make results reproducible. |
path |
Character string. The path to the folder, that is used for saving the checkpoints. |
... |
Additional arguments based to |
An object of class brmsfit
(with brmsfit = TRUE
)
or chkpt_brms
(with brmsfit = FALSE
)
## Not run: library(brms) library(cmdstanr) # path for storing checkpoint info path <- create_folder(folder_name = "chkpt_folder_fit1") # "random" intercept fit1 <- chkpt_brms(bf(formula = count ~ zAge + zBase * Trt + (1|patient), family = poisson()), data = epilepsy, , iter_warmup = 1000, iter_sampling = 1000, iter_per_chkpt = 250, path = path) # brmsfit output fit1 # path for storing checkpoint info path <- create_folder(folder_name = "chkpt_folder_fit2") # remove "random" intercept (for model comparison) fit2 <- chkpt_brms(bf(formula = count ~ zAge + zBase * Trt, family = poisson()), data = epilepsy, , iter_warmup = 1000, iter_sampling = 1000, iter_per_chkpt = 250, path = path) # brmsfit output fit2 # compare models loo(fit1, fit2) # using custom priors path <- create_folder(folder_name = "chkpt_folder_fit3") # priors bprior <- prior(constant(1), class = "b") + prior(constant(2), class = "b", coef = "zBase") + prior(constant(0.5), class = "sd") # fit model fit3 <- chkpt_brms( bf( formula = count ~ zAge + zBase + (1 | patient), family = poisson() ), data = epilepsy, path = path, prior = bprior, iter_warmup = 1000, iter_sampling = 1000, iter_per_chkpt = 250, ) # check priors prior_summary(fit3) ## End(Not run)
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.