ruspy.estimation.nfxp

This module contains functions for estimating the parameters shaping the cost function. Therefore it also contains the heart of this project. The python implementation of fix point algorithm developed by John Rust.

Functions

chain_rule_param(cost_dev, dev_ev_param, ...)
create_state_matrix(states, num_states)	This function constructs a auxiliary matrix for the log-likelihood of the cost parameters.
derivative_loglike_cost_params(params, ...)	sums up the Jacobian to obtain the gradient of the negative log likelihood function needed for algorithm such as the L-BFGS-B.
derivative_loglike_cost_params_individual(...)	This is the Jacobian of the individual log likelihood function of the cost parameter estimation with respect to all cost parameters needed for the BHHH.
get_ev(params, trans_mat, obs_costs, ...)	A auxiliary function, which allows the log-likelihood function as well as its derivative to share the same fixed point and to avoid the need to execute the computation double.
like_hood_data(l_values, decision_mat, state_mat)
like_hood_data_individual(l_values, ...)	generates the individual likelihood contribution based on the model.
like_hood_dev_values(p_choice, dev_values)
like_hood_vaules_rc(ev, costs, p_choice, ...)
log_like_values_param(ev, costs, p_choice, ...)
loglike_cost_params(params, maint_func, ...)	sums the individual negative log likelihood contributions for algorithms such as the L-BFGS-B.
loglike_cost_params_individual(params, ...)	This is the individual logliklihood function for the estimation of the cost parameters needed for the BHHH optimizer.