Simulated years of losses

Simulates n_sims years: a claim count from frequency, then that many independent losses from severity. Year i uses only stream i of the generator keyed by seed, so results do not depend on the number of threads and match Python and Rust.

Usage

simulate_events(frequency, severity, n_sims, seed)

Arguments

frequency

A poisson_count, negative_binomial_count or binomial_count.

severity

A lognormal, grid_distribution or Pareto-family severity (pareto, piecewise_pareto, log_affine_pareto, generalized_pareto).

n_sims

Number of simulated years.

seed

Generator seed: a non-negative whole number below 2^53.

Value

An event_set. Use events() for one year's losses, event_counts() for the number of losses per year, total() for the annual totals as a predictive_distribution, and apply_tower() for reinsurance.

Examples

ev <- simulate_events(poisson_count(5), lognormal_from_mean_cv(1000, 1), 10000, seed = 42)
ev@n_sims
#> [1] 10000
mean(total(ev))
#> [1] 4963.76