Creates coefficient matrices for which the characteristic polynomial corresponds to a stationary process. See Ansley and Kohn (1986) for details about the transformation used.
CoeffARMA(A, variance = NULL, ar = 1, ma = 0)An array of arbitrary square matrices in the multivariate case, or a vector of arbitrary numbers in the univariate case.
A variance - covariance matrix.
Note: variance not needed for the univariate case!
The order of the AR part.
The order of the MA part.
If multivariate, a list containing:
An array of coefficient matrices for the AR part.
An array of coefficient matrices for the MA part.
If univariate, a list containing:
A vector of coefficients for the AR part.
A vector of coefficients for the MA part.
Ansley CF, Kohn R (1986). “A note on reparameterizing a vector autoregressive moving average model to enforce stationarity.” Journal of Statistical Computation and Simulation, 24(2), 99--106.
CoeffARMA(A = stats::rnorm(2), ar = 1, ma = 1)
#> $ar
#> [1] -0.7055729
#>
#> $ma
#> [1] 0.7458205
#>