artsim {artfima}

Simulation of stationary ARTFIMA

Description

Simulation of stationary ARTFIMA, ARFIMA or ARIMA or bootstrap a fitted model. Useful for the parametric bootstrap.

Usage

artsim(n = 100, d = 0, lambda = 0, phi = numeric(0), 
    theta = numeric(0), mean = 0, sigma2 = 1, obj = NULL)

Arguments

n

length of time series

d

artfima difference parameter, real value greater than zero. If d=0, ARIMA model is used.

lambda

lambda artfima temper decay parameter, if lambda=0, ARFIMA model is simulated

phi

AR coefficients

theta

MA coefficients

mean

mean of series

sigma2

innovation variance

obj

output from artfima(). If obj is not output from artfima() then the other arguments are used to determine the time series parameters, except for the series length n.

Value

vector of length n, the simulated time series

Author(s)

A. I. McLeod, [e-mail]

References

McLeod, A.I., Yu, Hao and Krougly, Z. (2007). Algorithms for Linear Time Series Analysis: With R Package. Journal of Statistical Software 23/5 1-26.

Examples

z <- artsim(5000, d=5/6, lambda=0.045)
var(z)
artfimaTACVF(d=5/6, lambda=0.045, maxlag=1)[1]