JointAI (version 0.6.1)

add_samples: Continue sampling from an object of class JointAI

Description

This function allows to continue sampling from an existing object of class 'JointAI'. If the original sample was created using parallel computation, the separate 'jags' objects will be recompiled and sampling will again be performed in parallel.

Usage

add_samples(
  object,
  n.iter,
  add = TRUE,
  thin = NULL,
  monitor_params = NULL,
  progress.bar = "text",
  mess = TRUE
)

Arguments

object

object inheriting from class 'JointAI'

n.iter

the number of iterations of the MCMC chain (after adaptation; see also coda.samples)

add

logical; should the new MCMC samples be added to the existing samples or replace them? If samples are added, var.names is ignored.

thin

thinning interval (see window.mcmc)

monitor_params

named vector specifying which parameters should be monitored (see details)

progress.bar

character string specifying the type of progress bar. Possible values are "text", "gui", and "none" (see update). Note: when sampling is performed in parallel it is currently not possible to display a progress bar.

mess

logical; should messages be given? Default is TRUE. (Note: this applies only to messages given directly by JointAI.)

See Also

*_imp

The vignette Parameter Selection contains some examples on how to specify the argument monitor_params.

Examples

# NOT RUN {
# Example 1:
# Run an initial JointAI model:
mod <- lm_imp(y ~ C1 + C2, data = wideDF, n.iter = 100)

# Continue sampling:
mod_add <- add_samples(mod, n.iter = 200, add = TRUE)


# Example 2:
# Continue sampling, but additionally sample imputed values.
# Note: Setting different parameters to monitor than in the original model
# requires add = FALSE.
imps <- add_samples(mod, n.iter = 200, monitor_params = c("imps" = TRUE),
                    add = FALSE)

# }