Skip to contents

run_adoption_benchmarks() executes the named scenarios from adoption_benchmark_scenarios() through run_coverage_simulations() and attaches a summarise_benchmark_results() win/tie/loss summary. It is meant for opt-in benchmark runs, vignettes, and simulation reports rather than CRAN tests.

Usage

run_adoption_benchmarks(
  scenarios = adoption_benchmark_scenarios(),
  reps = 10L,
  methods = NULL,
  metrics = NULL,
  seed = 1L,
  write_results = FALSE,
  output_dir = file.path("results", "adoption_benchmarks"),
  ...
)

Arguments

scenarios

Scenario data frame from adoption_benchmark_scenarios() or character scenario names.

reps

Number of simulation replicates per scenario.

methods

Optional method vector overriding scenario defaults.

metrics

Optional metrics passed to summarise_benchmark_results().

seed

Base random seed.

write_results

Write CSV/RDS outputs from each simulation call.

output_dir

Directory for optional outputs.

...

Additional arguments passed to run_coverage_simulations(), such as iteration limits or elapsed-time limits.

Value

An object of class gamlss_longitudinal_adoption_benchmark with results, summary, and scenarios components.