In this paper we propose a strategy to decompose an ARFIMA model as a sum of linear stochastic models representing the short and long memory components. The procedure makes use of an approximate model obtained by replacing the fractional differencing operator by the ratio of two polynomials. Then, the unobserved components are derived by Decomel method and a real case study is examined.
A preliminary study on fractional time series decomposition / Corduas, Marcella; Piccolo, Domenico. - STAMPA. - 1:(2004), pp. 105-110.
A preliminary study on fractional time series decomposition
CORDUAS, MARCELLA;PICCOLO, DOMENICO
2004
Abstract
In this paper we propose a strategy to decompose an ARFIMA model as a sum of linear stochastic models representing the short and long memory components. The procedure makes use of an approximate model obtained by replacing the fractional differencing operator by the ratio of two polynomials. Then, the unobserved components are derived by Decomel method and a real case study is examined.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.