Title :
ARMA processes: order estimation
Author :
Ribeiro, M. Isabel ; Moura, Jose M F
Author_Institution :
CAPS, Lisbon, Portugal
Abstract :
The authors study, for an ARMA (autoregressive moving-average) ( p0, q0) process, the joint determination from a finite data sample of its structural parameters p0 and q0, its AR and MA components, and its innovation power σ2. The order estimation algorithm is based on the minimization of a functional d that measures the mismatch of the assumed model ARMA (p, q) to the data. The functional is evaluated from the estimated reflection coefficient sequence associated with the process. When the orders are decided, the proposed technique simultaneously provides the estimates of the AR and the MA coefficients as well as σ2
Keywords :
parameter estimation; signal processing; spectral analysis; ARMA processes; autoregressive coefficients; autoregressive moving-average; functional minimisation; innovation power; moving average coefficients; order estimation algorithm; parameter estimation; reflection coefficient sequence; Displays; Filters; Gaussian noise; Hydrogen; Poles and zeros; Power measurement; Reflection; Structural engineering; Technological innovation;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1988. ICASSP-88., 1988 International Conference on
Conference_Location :
New York, NY
DOI :
10.1109/ICASSP.1988.197100