This section describes subroutines that are related to fractionally integrated time series analysis. The phenomenon of long memory can be observed in hydrology, finance, economics, and other fields. Unlike what occurs in a stationary process, the correlations between observations of a long-memory series slowly decay to zero.
The following subroutines are supported:
computes the autocovariance function for a fractionally integrated ARMA model.
estimates the parameters for a fractionally integrated ARMA model.
computes the log-likelihood function for a fractionally integrated ARMA model.
generates a fractionally integrated ARMA process.
computes a fractionally differenced process.