smc2_control: Control for SMC2

In mrc-ide/mcstate: Monte Carlo Methods for State Space Models

Control for SMC2

Description

Control for smc2. This function constructs a list of options and does some basic validation to ensure that the options will work well together. Do not manually change the values in this object. Do not refer to any argument except n_parameter_sets by position as the order of the arguments may change in future.

Usage

smc2_control(
  n_parameter_sets,
  degeneracy_threshold = 0.5,
  covariance_scaling = 0.5,
  progress = TRUE,
  save_trajectories = FALSE
)

Arguments

n_parameter_sets	The number of replicate parameter sets to simulate at once.
degeneracy_threshold	The degeneracy threshold. Once the effective sample size drops below degeneracy_threshold * n_parameter_sets the algorithm will rerun simulations from the beginning of the data and use these to replenish the particles.
covariance_scaling	A scaling factor to update variance covariance matrix of sampled parameters by
progress	Logical, indicating if a progress bar should be displayed, using progress::progress_bar.
save_trajectories	Logical, indicating if particle trajectories should be saved during the simulation.

Value

A smc2_control object, which should not be modified once created.

Examples

mcstate::smc2_control(100)

mrc-ide/mcstate documentation built on July 3, 2024, 1:34 p.m.