The Correlogram of a Long Memory Process Plus a Simple Noise

Clive W.J. Granger and Francesc Marmol

UCSD Economics Discussion Paper 97-29
November 1997

Abstract

A frequent property of data, particularly in the financial area, is that the correlogram is low but remains positive for many lags. A plausible explanation for this is that the process consists of a stationary, long memory component plus a white noise component of much larger variance. The implications of such a composition are explored including the consequences for estimation of the long memory parameter.


Back to 1997 Discussion Paper Titles