论文信息 - Recursive methods for estimating multiple missing values of a multivariate stationary process

Recursive methods for estimating multiple missing values of a multivariate stationary process

Existing methods for estimating linearly s future values of a m-variate stationary random process using a record of p vectors from the past consist in first solving the one-step prediction problem and then all the h-step prediction problems for 2/spl les/h/spl les/s independently. When the Levinson (1947) algorithm is used, each prediction problem is solved with a numerical complexity proportional to p/sup 2/. We propose new methods to solve the h-step prediction problems for h/spl ges/2 with a numerical complexity proportional to p.

Diego P. Ruiz | Antolino Gallego | Pascal Bondon

[1] P. Whittle. On the fitting of multivariate autoregressions, and the approximate canonical factorization of a spectral density matrix , 1963 .

[2] J. L. Hock,et al. An exact recursion for the composite nearest‐neighbor degeneracy for a 2×N lattice space , 1984 .

[3] Charles L. Lawson,et al. Solving least squares problems , 1976, Classics in applied mathematics.

[4] James Durbin,et al. The fitting of time series models , 1960 .

[5] N. Levinson. The Wiener (Root Mean Square) Error Criterion in Filter Design and Prediction , 1946 .

[6] G. Tunnicliffe Wilson,et al. Interpolating Time Series with Application to the Estimation of Holiday Effects on Electricity Demand , 1976 .

[7] B. Abraham. Missing observations in time series , 1981 .

[8] N. Wiener. The Wiener RMS (Root Mean Square) Error Criterion in Filter Design and Prediction , 1949 .

[9] Richard A. Davis,et al. Time Series: Theory and Methods , 2013 .