statsmodels.regression.linear_model.burg¶

statsmodels.regression.linear_model.burg(endog, order=1, demean=True)[source]¶

Compute Burg’s AP(p) parameter estimator.

Parameters:¶

endog : array_like¶

The endogenous variable.

order : int, optional¶

Order of the AR. Default is 1.

demean : bool, optional¶

Flag indicating to subtract the mean from endog before estimation.

Returns:¶

• rho (ndarray) – The AR(p) coefficients computed using Burg’s algorithm.

• sigma2 (float) – The estimate of the residual variance.

See also

yule_walker

Estimate AR parameters using the Yule-Walker method.

Notes

AR model estimated includes a constant that is estimated using the sample mean (see [1]). This value is not reported.

References

Examples

>>> import statsmodels.api as sm
>>> from statsmodels.datasets.sunspots import load
>>> data = load()
>>> rho, sigma2 = sm.regression.linear_model.burg(data.endog, order=4)

>>> rho
array([ 1.30934186, -0.48086633, -0.20185982,  0.05501941])
>>> sigma2
271.2467306963966