statsmodels.discrete.discrete_model.MNLogit.fit_constrained

MNLogit.fit_constrained(constraints, start_params=None, **fit_kwds)

Fit a constrained model and return a results instance

This is a development version for fit_constrained methods or fit_constrained as standalone function.

It will not work correctly for all models because creating a new results instance is not standardized for use outside the fit methods, and might need adjustments for this.

This is the prototype for the fit_constrained method that has been added to Poisson and GLM.

Parameters:

modelmodel instance

An instance of a model that supports fit_constrained.

constraintsstr, tuple or array_like

Constraints as accepted by FormulaManager.get_linear_constraints, e.g. a string, a sequence of strings, or a tuple (R, q).

start_paramsNone or array_like

Starting values for the optimization, in the original parameter space.

**fit_kwdskeyword arguments

Keyword arguments used in the optimization of the transformed model.

Returns:

Results

A results wrapper instance with the constrained parameter estimates and covariance.