Run a DGP × estimator grid over multiple seeds

Usage

cs_run_grid(
  dgp_ids,
  estimator_ids,
  n,
  seeds,
  tau = NULL,
  version = NULL,
  status = "stable",
  bootstrap = FALSE,
  B = 200L,
  config = list(),
  board = NULL,
  skip_existing = FALSE,
  force = FALSE,
  max_runtime = Inf,
  parallel = FALSE,
  experimental_parallel = FALSE,
  staging_dir = NULL,
  show_progress = FALSE
)

Arguments

dgp_ids: Character vector of DGP IDs (must exist in cs_dgp_registry()).
estimator_ids: Character vector of estimator IDs (must exist in cs_estimator_registry()).
n: Integer, sample size per run (same for all combinations).
seeds: Integer vector of seeds to run for each (DGP, estimator) pair.
tau: Optional numeric vector of quantile levels (forwarded to cs_run_single()).
version: Optional DGP version string; forwarded to cs_get_dgp().
status: Optional DGP status filter; forwarded to cs_get_dgp().
bootstrap: Logical, whether to run bootstrap for ATT CIs.
B: Integer, number of bootstrap replicates.
config: Optional named list of configuration settings (forwarded to cs_run_single()).
board: Optional pins board for persistence.
skip_existing: Logical, whether to resume from existing pins.
force: Logical, whether to overwrite existing pins (alias for skip_existing = FALSE).
max_runtime: Numeric scalar; maximum allowed runtime (seconds) per seed.
parallel: Logical; if TRUE, uses furrr/future for parallel execution.
experimental_parallel: Logical; must be TRUE to enable parallel mode.
staging_dir: Optional staging directory for crash recovery.
show_progress: Logical; whether to display per-seed progress messages.

Value

A tibble with one flattened analysis row per (dgp_id, estimator_id, seed) run, including qst and scores list columns, suitable for cs_summarise_runs().