ARMA spectral density
Purpose
Description
Macro Synopsis
Modules
Related Functions
References
Purpose
ARMA power spectrum
Description
This function fits an Auto-Regressive Moving Average (ARMA)
process of a given finite order to the given signal from which the spectrum is obtained analytically.
The spectrum of an ARMA process with model orders P and Q is
given by:
Parameters for ARMA spectral density are
- order P of the AR process,
- order Q of the MA process and
- frequency resolution freqres as number of points on the
frequency axis.
The estimated ARMA model coefficients will appear in the message
window.
ARMA spectral density provides a high frequency resolution and consumes little
computational power, but tends to be less robust than other methods of
frequency analysis and makes it more difficult to give an absolute
measure of spectral power.
Macro Synopsis
y = ARMAspect(x,P,Q,freqres);
signal x,y;
int P,Q,freqres;
Modules
Statistics
Related Functions
AR simulation, ARIMA modeling,
ARIMAX modeling, ARMA model order,
ARMA modeling, ARMA simulation,
ARMAX modeling,
ARMAX simulation, NAR modeling,
NARMA modeling.
References
Ljung [10], Grenader/Rosenblatt
[15], Conover [11], Graybill
[12], Hollander/Wolfe [13].