Stationarity (Covariance Stationarity, Weak Stationarity)
If neither the mean μ_t nor the autocovariances γ_jt depend on the date t, then the process for Y_t is said to be covariance-stationary or weakly stationary:
E(Y_t) = μ for all t
E(Y_t ー μ)(Y_t-1 ー μ) = γ_j for all t and j
Hamilton, 1994, Time Series Analysis
参考
http://www.econ.hit-u.ac.jp/~tanaka/ecmr/chap1.pdf
0 件のコメント:
コメントを投稿