ruspy.estimation.nfxp.derivative_loglike_cost_params
- ruspy.estimation.nfxp.derivative_loglike_cost_params(params, maint_func, maint_func_dev, num_states, trans_mat, state_mat, decision_mat, disc_fac, scale, alg_details)[source]
sums up the Jacobian to obtain the gradient of the negative log likelihood function needed for algorithm such as the L-BFGS-B.
- Parameters
- params
numpy.ndarray
see Cost parameters
- maint_func: func
- maint_func_dev: func
- num_states
python:int
The size of the state space.
- trans_mat
numpy.ndarray
- state_mat
numpy.ndarray
see State matrix
- decision_mat
numpy.ndarray
see Decision Matrix
- disc_fac
numpy.float
see Discount factor
- scale
numpy.float
see Scale
- alg_details
python:dict
see :ref: alg_details
- params
- Returns
dev
numpy.ndarray
A dimension(params) sized vector containing the gradient of the negative likelihood function.