出版社：Suntory Toyota International Centres for Economics and Related Disciplines
摘要：This paper introduces a nonparametric Granger-causality test for covariancestationary linear processes under, possibly, the presence of long-rangedependence. We show that the test is consistent and has power againstcontiguous alternatives converging to the parametric rate T-½. Since the test isbased on estimates of the parameters of the representation of a VAR modelas a, possibly, two-sided infinite distributed lag model, we first show that amodification of Hannan's (1963, 1967) estimator is root-T consistent andasymptotically normal for the coefficients of such a representation. When thedata is long-range dependent this method of estimation becomes moreattractive than Least Squares, since the latter can be neither root-T consistentnor asymptotically normal as is the case with short-range dependent data
关键词：Causality; long-range dependence; spectral analysis; distributed;lag model; consistent test
