quentinandre / john-rust-1987-python Goto Github PK

Recreation of the "Optimal Replacement of GMC Bus Engines" paper by J. Rust, describing a single-agent dynamic optimization model.

License: MIT License

Python 0.64% Jupyter Notebook 99.02% CSS 0.34%

john-rust-1987-python's People

Stargazers

Watchers

john-rust-1987-python's Issues

beta argument in `self.loglike`

Should the following function have a beta argument (or a **kwargs) that is passed to self.fl_costs?

John-Rust-1987-Python/dynamiclogit.py

Lines 207 to 222 in 2e1a6e1

 def loglike(self, params): 

 """ 

  The log-likelihood of the Dynamic model is estimated in several steps. 

  1°) The currenter parameters are supplied to the contraction mapping  

  function 

  2°) The function returns a matrix of decision probabilities for each  

  state. 

  3°) This matrix is used to compute the loglikelihood of the  

  observations 

  4°) The log-likelihood are then summed accross individuals, and  

  returned 

  """ 

 util = self.fl_costs(params, suppr_output=True) 

 pchoice = self.choice_prob(util) 

 logprob = np.log(np.dot(pchoice.T, self.state_mat)) 

 return -np.sum(self.dec_mat*logprob)

quentinandre / john-rust-1987-python Goto Github PK

john-rust-1987-python's People

Stargazers

Watchers

Forkers

john-rust-1987-python's Issues

beta argument in `self.loglike`

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent

	def loglike(self, params):
	"""
	The log-likelihood of the Dynamic model is estimated in several steps.
	1°) The currenter parameters are supplied to the contraction mapping
	function
	2°) The function returns a matrix of decision probabilities for each
	state.
	3°) This matrix is used to compute the loglikelihood of the
	observations
	4°) The log-likelihood are then summed accross individuals, and
	returned
	"""
	util = self.fl_costs(params, suppr_output=True)
	pchoice = self.choice_prob(util)
	logprob = np.log(np.dot(pchoice.T, self.state_mat))
	return -np.sum(self.dec_mat*logprob)