Convenience wrapper around margot_rate_batch(). Returns two data frames, both sorted by descending RATE Estimate, with reliable results highlighted in bold.
Usage
margot_rate(
models,
model_names = NULL,
policy = c("treat_best", "withhold_best"),
round_digits = 3,
highlight_significant = TRUE,
label_mapping = NULL,
remove_tx_prefix = TRUE,
remove_z_suffix = TRUE,
use_title_case = TRUE,
remove_underscores = TRUE,
adjust = NULL,
alpha = 0.05,
apply_adjustment = !is.null(adjust),
seed = 12345
)Arguments
- models
List from margot_causal_forest().
- model_names
Optional character vector specifying which models to process. Default NULL (all models).
- policy
Character; "treat_best" (default) or "withhold_best".
- round_digits
Integer; decimal places (default 3).
- highlight_significant
Logical; bold outcomes whose 95 percent CI excludes 0 (default TRUE). Note: Only positive significant effects are bolded, negative effects are not bolded.
- label_mapping
Named character vector for converting variable names to readable labels.
- remove_tx_prefix
Logical; remove treatment prefix from variable names (default TRUE).
- remove_z_suffix
Logical; remove z-score suffix from variable names (default TRUE).
- use_title_case
Logical; convert variable names to title case (default TRUE).
- remove_underscores
Logical; replace underscores with spaces (default TRUE).
- adjust
Character; method for adjusting p-values, passed to stats::p.adjust(). Options include "holm", "hochberg", "hommel", "bonferroni", "BH", "BY", "fdr", "none". Default is NULL (no adjustment).
- alpha
Numeric; significance threshold (default 0.05).
- apply_adjustment
Logical; if TRUE, compute p-values and apply adjustment method. If FALSE, just document the adjustment method without recomputing. Default is TRUE when adjust parameter is provided, FALSE otherwise.
- seed
Integer; base seed for reproducible RATE computations (default 12345).