statsmodels.tsa.regime_switching.markov_regression.MarkovRegression.filter¶

MarkovRegression.filter(params, transformed=True, cov_type=None, cov_kwds=None, return_raw=False, results_class=None, results_wrapper_class=None)¶

Apply the Hamilton filter

Parameters:¶

paramsarray_like

Array of parameters at which to perform filtering.

transformedbool, optional

Whether or not params is already transformed. Default is True.

cov_typestr, optional

See fit for a description of covariance matrix types for results object.

cov_kwdsdict or None, optional

See fit for a description of required keywords for alternative covariance estimators

return_rawbool,optional

Whether or not to return only the raw Hamilton filter output or a full results object. Default is to return a full results object.

results_classtype, optional

A results class to instantiate rather than MarkovSwitchingResults. Usually only used internally by subclasses.

results_wrapper_classtype, optional

A results wrapper class to instantiate rather than MarkovSwitchingResults. Usually only used internally by subclasses.

Returns:¶

MarkovSwitchingResults