Combine brmsfit objects saved as RDS files.

combine_rds_fits checks brmsfit objects saved as RDS files.

combine_rds_fits(path, dest.path = ".", save = TRUE, name = NULL, overwrite = FALSE,
suffix = "-combined_model", check.data = TRUE, verbose = TRUE, summary = FALSE, ...)

Arguments

path

Directory in which to look for .rds files. Required.

dest.path

Directory in which to save the combined fit as a RDS file (if save = TRUE). Default is the current working directory.

save

Logical to control if the combined fit is saved as a RDS file.

name

Character string with the name of RDS file to be saves (when save = TRUE)..

overwrite

Logical to control if the RDS file is overwritten (when save = TRUE).

suffix

Character string with a suffix to be added to the file name (when save = TRUE). Default is "-combined_model".

check.data

Logical. Controls if the data should be checked for being the same across models (as in brm).

verbose

Logical to control if messages are printed into the console.

summary

Logical to control if a summary of the combined model is also saved. If TRUE extended_summary is used.

...

Additional arguments to be passed to extended_summary for further customizing summary.

Value

If save = TRUE the combined fit is save as a RDS file, otherwise the function returns a brmsfit object.

Details

The function takes several brms models stored as RDS files and combine them in a single model. By default the combined model is saved as a RDS file, but it can instead be returned as an object (if save = FALSE). If not supplied the name is obtained from the containing folder.

References

Araya-Salas (2022), brmsish: miscellaneous functions to customize brms bayesian regression models. R package version 1.0.0.Paul-Christian Buerkner (2017). brms: An R Package for Bayesian Multilevel Models Using Stan. Journal of Statistical Software, 80(1), 1-28. doi:10.18637/jss.v080.i01

See also

extended_summary, check_rds_fits

Author

Marcelo Araya-Salas marcelo.araya@ucr.ac.cr)

Examples

{
# create directory
dir.create(file.path(tempdir(), "rdss"))
# run 2 models
md1 <- brm(Petal.Length ~ Petal.Width + Species, iris, chains = 1,
iter = 500, file = file.path(tempdir(), "rdss", "md1"))

md2 <- brm(Petal.Length ~ Species, iris, chains = 1, iter = 500,
file = file.path(tempdir(), "rdss", "md2"))

# check fits
combine_rds_fits(path = file.path(tempdir(), "rdss"))
}
#> Warning: '/tmp/RtmpunyEM3/rdss' already exists
#> Compiling Stan program...
#> Error in .fun(model_code = .x1): Boost not found; call install.packages('BH')