sim: Simulate Time Series from ARIMA or Transfer Function Models

In tfarima: Transfer Function and ARIMA Models

Simulate Time Series from ARIMA or Transfer Function Models

Description

Generates random time series from ARIMA (um) or transfer function (tfm) models.

Usage

## S3 method for class 'tfm'
sim(
  mdl,
  n = 100,
  z0 = NULL,
  n0 = 0,
  a = NULL,
  seed = NULL,
  envir = parent.frame(),
  ...
)

sim(mdl, ...)

## S3 method for class 'um'
sim(
  mdl,
  n = 100,
  z0 = NULL,
  n0 = 0,
  a = NULL,
  seed = NULL,
  envir = parent.frame(),
  ...
)

Arguments

mdl	An object of class um or tfm.
n	Number of observations to simulate.
z0	Initial conditions for nonstationary series. Default is NULL (zero initial conditions).
n0	Number of initial observations to discard as burn-in. Default is 0.
a	Optional vector of innovations with length n + n0. If NULL, innovations are drawn from N(0, \sigma^2).
seed	Random seed for reproducibility.
envir	Environment for argument evaluation. Default is parent.frame().
...	Additional arguments.

Value

A ts object with the simulated time series.

See Also

sim.um, sim.tfm

Examples

# AR(1) model
mdl1 <- um(ar = "1 - 0.8B", sig2 = 1)
z1 <- sim(mdl1, n = 100, seed = 123)

# ARIMA(0,1,1) with burn-in
mdl2 <- um(i = 1, ma = "1 - 0.5B", sig2 = 1)
z2 <- sim(mdl2, n = 100, n0 = 50, seed = 456)

tfarima documentation built on Nov. 5, 2025, 7:43 p.m.