LONG-RUN COVARIANCE MATRICES FOR FRACTIONALLY INTEGRATED PROCESSES
给出了平稳长记忆向量过程自协方差矩阵的渐近展开式，并应用于推导多元长记忆时间序列的长协方差矩阵公式，对计量经济学和统计学研究者有用。
An asymptotic expansion is given for the autocovariance matrix of a vector of stationary long-memory processes with memory parameters d ∈ [0,½). The theory is then applied to deliver formulas for the long-run covariance matrices of multivariate time series with long memory.Phillips acknowledges partial support from a Kelly Fellowship and from the NSF under grant SES 04-142254.This may be proved directly using a Fourier integral asymptotic expansion when the spectrum of the short-memory component is analytic.