出版社：Suntory Toyota International Centres for Economics and Related Disciplines
摘要：Sufficient conditions for strict stationarity of ARCH(.) are established, withoutimposing covariance stationarity and for any specification of the conditionalsecond moment coefficients. GARCH(p,q) as well as the case ofhyperbolically decaying coefficients are included, such as the autoregressivecoefficients of ARFIMA(p,d,q), once the non-negativity constraints areimposed. Second, we show the necessary and sufficient conditions forcovariance stationarity of ARCH(.), both for the levels and the squares.These prove to be much stronger than the strict stationarity conditions. Thecovariance stationarity condition for the levels rules out long memory in thesquares
关键词：ARCH(.); GARCH(;p;q;); nonlinear moving average;representation; strict and weak stationarity; memory
