vector with the specification of the ARMA model: the two integer components (p, q) are the AR order and the MA order.
ar.order, ma.order
AR and MA polimonial order, respectively. See details below.
sd.order
polinomial order noise scale factor.
d.order
d polinomial order, where d is the ARFIMA parameter.
include.d
logical argument for ARFIMA models. If include.d=FALSE then the model is an ARMA process.
N
value corresponding to the length of the window to compute periodogram. If N=NULL then the function will use N = \textmd{trunc}(n^{0.8}), see Dahlhaus (1998) where n is the length of the y vector.
S
value corresponding to the lag with which will go taking the blocks or windows.
include.taper
logical argument that by default is TRUE. See periodogram.
Details
The estimation of the time-varying parameters can be carried out by means of the Whittle log-likelihood function proposed by Dahlhaus (1997),
where M is the number of blocks, N the length of the series per block, n =S(M-1)+N, S is the shift from block to block, u_j =t_j/n, t_j =S(j-1)+N/2, j =1,…,M and λ the Fourier frequencies in the block (2,π,k/N, k = 1,…, N).
Author(s)
Ricardo Olea <raolea@uc.cl>
References
Dahlhaus, R. Fitting time series models to nonstationary processes. The Annals of Statistics. 1997; Vol. 25, No. 1:1-37.
Olea R, Palma W. An efficient estimator for locally stationary gaussian long-memory processes. The Annals of Statistics. 2010; Vol. 38, No. 5:2958-2997.