TacvfMA {FitAR} | R Documentation |
The theoretical autocovariance function of a MA(q) with unit variance is computed.
TacvfMA(theta, lag.max = 20)
theta |
q parameters in MA(q) |
lag.max |
number of lags required. |
The first q+1 values are determined using a matrix multiplication - avoiding a loop. The remaining values set to zero.
Vector of length q+1 containing the autocovariances at lags 0,1,...,lag.max
See Details in TacvfAR
for why we prefer
to use this algorithm instead of ARMAacf
A.I.McLeod
McLeod, A.I. and Zhang, Y. (2006), Partial autocorrelation parameterization for subset autoregression. Journal of Time Series Analysis, 27, 599-612.
TacvfMA(c(1.8,,-0.9),10)