B. M. Bell and D. B. Percival (1991), `A Two Step Burg Algorithm,' IEEE Transactions on Signal Processing, 39, no. 1, pp. 185-9.
We consider the problem of estimating the parameters of a real-valued, stationary, non-deterministic, autoregressive process of order p from a time series of finite length. Burg's algorithm estimates these parameters indirectly by sequentially estimating one reflection coefficient at a time. Our approach is to sequentially estimate the reflection coefficients in pairs. Our new algorithm has the same order of computational complexity as Burg's; is guaranteed to generate parameter estimates which correspond to a stationary process (as does Burg's); and produces spectral density estimates which do not appear to suffer from spectral line splitting - in contrast to Burg's algorithm.
Autoregressive processes; Harmonic analysis; Line splitting; Spectral estimation
Go to next summary or home page for Don Percival