An adaptive Monte Carlo algorithm for computing mixed logit estimators

2006 ◽  
Vol 3 (1) ◽  
pp. 55-79 ◽  
Author(s):  
Fabian Bastin ◽  
Cinzia Cirillo ◽  
Philippe L. Toint
Keyword(s):  
Monte Carlo ◽  
Mixed Logit ◽  
Monte Carlo Algorithm ◽  
Adaptive Monte Carlo

Application of an adaptive Monte Carlo algorithm to mixed logit estimation

2006 ◽  
Vol 40 (7) ◽  
pp. 577-593 ◽  
Author(s):  
Fabian Bastin ◽  
Cinzia Cirillo ◽  
Philippe L. Toint
Keyword(s):  
Monte Carlo ◽  
Mixed Logit ◽  
Monte Carlo Algorithm ◽  
Adaptive Monte Carlo ◽  
Logit Estimation

scholarly journals Adaptive Monte Carlo algorithm to global radio resources optimization in H-CRAN

2017 ◽  
Author(s):  
Matias A. K. Schimuneck ◽  
Maicon Kist ◽  
Juergen Rochol ◽  
Ana Carolina Ribeiro-Teixeira ◽  
Cristiano Bonato Both
Keyword(s):  
Monte Carlo ◽  
Monte Carlo Algorithm ◽  
Adaptive Monte Carlo ◽  
Radio Resources

Adaptive Monte Carlo algorithm for Wigner kernel evaluation

2019 ◽  
Vol 32 (14) ◽  
pp. 9953-9964
Author(s):  
Venelin Todorov ◽  
Ivan Dimov ◽  
Rayna Georgieva ◽  
Stoyan Dimitrov
Keyword(s):  
Monte Carlo ◽  
Monte Carlo Algorithm ◽  
Adaptive Monte Carlo

Evaluation of Optimization Methods for Estimating Mixed Logit Models

2005 ◽  
Vol 1921 (1) ◽  
pp. 35-43 ◽  
Author(s):  
Fabian Bastin ◽  
Cinzia Cirillo ◽  
Stephane Hess
Keyword(s):  
Monte Carlo ◽  
Optimization Algorithm ◽  
Monte Carlo Methods ◽  
Likelihood Function ◽  
Stated Preference ◽  
Mixed Logit ◽  
Trust Region ◽  
Monte Carlo Algorithm ◽  
Preference Data ◽  
Quasi Monte Carlo

The performances of different simulation-based estimation techniques for mixed logit modeling are evaluated. A quasi–Monte Carlo method (modified Latin hypercube sampling) is compared with a Monte Carlo algorithm with dynamic accuracy. The classic Broyden–Fletcher–Goldfarb–Shanno (BFGS) optimization algorithm line-search approach and trust region methods, which have proved to be extremely powerful in nonlinear programming, are also compared. Numerical tests are performed on two real data sets: stated preference data for parking type collected in the United Kingdom, and revealed preference data for mode choice collected as part of a German travel diary survey. Several criteria are used to evaluate the approximation quality of the log likelihood function and the accuracy of the results and the associated estimation runtime. Results suggest that the trust region approach outperforms the BFGS approach and that Monte Carlo methods remain competitive with quasi–Monte Carlo methods in high-dimensional problems, especially when an adaptive optimization algorithm is used.

Sign in / Sign up

Export Citation Format

Share Document