statsmodels.tsa.statespace.varmax.VARMAX.hessian¶

VARMAX.hessian(params, *args, **kwargs)¶

Hessian matrix of the likelihood function, evaluated at the given parameters

Parameters:¶

params : array_like¶

Array of parameters at which to evaluate the hessian.

*args¶

Additional positional arguments to the loglike method.

**kwargs¶

Additional keyword arguments to the loglike method.

Returns:¶

hessian – Hessian matrix evaluated at params

Return type:¶

ndarray

Notes

This is a numerical approximation.

Both args and kwargs are necessary because the optimizer from fit must call this function and only supports passing arguments via args (for example scipy.optimize.fmin_l_bfgs).