statsmodels.regression.linear_model.GLS.fit

GLS.fit(method='pinv', cov_type='nonrobust', cov_kwds=None, use_t=None, **kwargs)

Full fit of the model.

The results include an estimate of covariance matrix, (whitened) residuals and an estimate of scale.

Parameters

methodstr, optional

Can be “pinv”, “qr”. “pinv” uses the Moore-Penrose pseudoinverse to solve the least squares problem. “qr” uses the QR factorization.

cov_typestr, optional

See regression.linear_model.RegressionResults for a description of the available covariance estimators.

cov_kwdslist or None, optional

See linear_model.RegressionResults.get_robustcov_results for a description required keywords for alternative covariance estimators.

use_tbool, optional

Flag indicating to use the Student’s t distribution when computing p-values. Default behavior depends on cov_type. See linear_model.RegressionResults.get_robustcov_results for implementation details.

**kwargs

Additional keyword arguments that contain information used when constructing a model using the formula interface.

Returns

RegressionResults

The model estimation results.

See also

RegressionResults

The results container.

RegressionResults.get_robustcov_results

A method to change the covariance estimator used when fitting the model.

Notes

The fit method uses the pseudoinverse of the design/exogenous variables to solve the least squares minimization.