A new spectrum extension method that maximizes the multistep minimum prediction error-generalization of the maximum entropy concept

摘要

Given (n+1) consecutive autocorrelations of a stationary discrete-time stochastic process, how this finite sequence is extended so that the power spectral density associated with the resulting infinite sequence of correlations is nonnegative everywhere is discussed. It is well known that when the Hermitian Toeplitz matrix generated from the given autocorrelations is positive definite, the problem has an infinite number of solutions and the particular solution that maximizes the entropy functional results in a stable all-pole model of order n. Since maximization of the entropy functional is equivalent to maximization of the minimum mean-square error associated with one-step predictors, the problem of obtaining admissible extensions that maximize the minimum mean-square error associated with k-step (k>or=n) predictors, that are compatible with the given autocorrelations, is studied. It is shown that the resulting spectrum corresponds to that of a stable autoregressive moving average (ARMA) (n, k-1) process.