gsignal (version 0.3-1)

pburg: Autoregressive PSD estimate - Burg's method

Description

Calculate Burg maximum-entropy power spectral density.

Usage

pburg(
  x,
  p,
  criterion = NULL,
  freq = 256,
  fs = 1,
  range = NULL,
  method = if (length(freq) == 1 && bitwAnd(freq, freq - 1) == 0) "fft" else "poly"
)

Arguments

x

input data, specified as a numeric or complex vector or matrix. In case of a vector it represents a single signal; in case of a matrix each column is a signal.

p

model order; number of poles in the AR model or limit to the number of poles if a valid criterion is provided. Must be < length(x) - 2.

criterion

model-selection criterion. Limits the number of poles so that spurious poles are not added when the whitened data has no more information in it. Recognized values are:

"AKICc"

approximate corrected Kullback information criterion (recommended)

"KIC"

Kullback information criterion

"AICc"

corrected Akaike information criterion

"AIC"

Akaike information criterion

"FPE"

final prediction error

The default is to NOT use a model-selection criterion (NULL)

freq

vector of frequencies at which power spectral density is calculated, or a scalar indicating the number of uniformly distributed frequency values at which spectral density is calculated. Default: 256.

fs

sampling frequency (Hz). Default: 1

range

character string. one of:

"half" or "onesided"

frequency range of the spectrum is from zero up to but not including fs / 2. Power from negative frequencies is added to the positive side of the spectrum.

"whole" or "twosided"

frequency range of the spectrum is -fs / 2 to fs / 2, with negative frequencies stored in "wrap around order" after the positive frequencies; e.g. frequencies for a 10-point "twosided" spectrum are 0 0.1 0.2 0.3 0.4 0.5 -0.4 -0.3 -0.2. -0.1.

"shift" or "centerdc"

same as "whole" but with the first half of the spectrum swapped with second half to put the zero-frequency value in the middle. If freq is a vector, "shift" is ignored.

Default: If model coefficients a are real, the default range is "half", otherwise the default range is "whole".

method

method used to calculate the power spectral density, either "fft" (use the Fast Fourier Transform) or "poly" (calculate the power spectrum as a polynomial). This argument is ignored if the freq argument is a vector. The default is "poly" unless the freq argument is an integer power of 2.

Value

An object of class "ar_psd" , which is a list containing two elements, freq and psd containing the frequency values and the estimates of power-spectral density, respectively.

See Also

ar_psd, arburg

Examples

# NOT RUN {
A <- Arma(1, c(1, -2.7607, 3.8106, -2.6535, 0.9238))
y <- filter(A, 0.2 * rnorm(1024))
plot(pb <- pburg(y, 4))

# }