simulate: Simulation of a spatiotemporal partially-observed Markov...

In spatPomp: Inference for Spatiotemporal Partially Observed Markov Processes

Simulation of a spatiotemporal partially-observed Markov process

Description

simulate generates simulations of the latent and measurement processes.

Usage

## S4 method for signature 'spatPomp'
simulate(
  object,
  nsim = 1,
  seed = NULL,
  format = c("spatPomps", "data.frame"),
  include.data = FALSE,
  ...
)

Arguments

object	optional; if present, it should be a data frame or a ‘pomp’ object.
nsim	number of simulations.
seed	optional integer; if set, the pseudorandom number generator (RNG) will be initialized with seed. The RNG will be restored to its original state afterward.
format	the format of the simulated results. If the argument is set to 'spatPomps', the default behavior, then the output is a list of spatPomp objects. Options are 'spatPomps' and 'data.frame'.
include.data	if TRUE, the original data and covariates (if any) are included (with .id = "data"). This option is ignored unless format = "data.frame".
...	additional arguments are passed to pomp.

Value

if format='spatPomps' and nsim=1 an object of class ‘spatPomp’ representing a simulation from the model in object is returned. If format='spatPomps' and nsim>1 a list of class ‘spatPomp’ objects is returned. If format='data.frame' then a class ‘data.frame’ object is returned.

Author(s)

Kidus Asfaw

References

\asfaw

2020

Examples

# Complete examples are provided in the package tests
## Not run: 
# Get a spatPomp object
b <- bm(U=2, N=5)
# Get 2 simulations from same model as data.frame
sims <- simulate(b, nsim=2, format='data.frame')

## End(Not run)

spatPomp documentation built on Sept. 11, 2024, 9:16 p.m.