Summarizes each parameter estimate, showing you the quantiles passed to
probs
, and optionally the estimates of .orig_mod
.
param_estimates_compare(
.boot_sum,
.orig_mod = NULL,
.compare_cols = starts_with(c("THETA", "SIGMA", "OMEGA")),
probs = c(0.5, 0.025, 0.975),
na.rm = FALSE
)
# S3 method for bbi_nmboot_summary
param_estimates_compare(
.boot_sum,
.orig_mod = NULL,
.compare_cols = NULL,
probs = c(0.5, 0.025, 0.975),
na.rm = FALSE
)
# S3 method for default
param_estimates_compare(
.boot_sum,
.orig_mod = NULL,
.compare_cols = starts_with(c("THETA", "SIGMA", "OMEGA")),
probs = c(0.5, 0.025, 0.975),
na.rm = FALSE
)
Either a bbi_nmboot_summary
object, or a tibble with
columns for each parameter and rows for each model (like what's returned
from param_estimates_batch()
).
bbi_model
object to compare .boot_sum
against. This will
be automatically set if passing in a bbi_nmboot_summary
object.
An expression that can be passed to dplyr::select()
to
select which columns in .boot_sum
will be pivoted and summarized. See
?tidyselect::language
for more details and options. Only used if .boot_sum
is a tibble.
Numeric vector with values between 0 and 1 to be passed through to
stats::quantile()
. Represents the quantiles to calculate for parameter
estimates in .boot_sum
.
Logical scalar, passed through to stats::quantile()
.
A tibble containing quantiles for each parameter estimate, optionally
compared to the estimates from .orig_mod
.
if (FALSE) {
# Via a bootstrap run
boot_run <- read_model(file.path(MODEL_DIR, "1-boot"))
boot_sum <- summarize_bootstrap_run(boot_run)
param_estimates_compare(boot_sum)
# Via a custom table
orig_mod <- read_model(file.path(MODEL_DIR, "1"))
param_df <- param_estimates_batch(MODEL_DIR)
param_estimates_compare(param_df, .orig_mod = orig_mod)
}