biogeme 3.2.6 [2020-06-02]

Python package

Home page:

Submit questions to

Michel Bierlaire, Transport and Mobility Laboratory, Ecole Polytechnique Fédérale de Lausanne (EPFL)

This file has automatically been generated on 2020-06-02 10:38:20.475329

If you drag this HTML file into the Calc application of OpenOffice, or the spreadsheet of LibreOffice, you will be able to perform additional calculations.

Report file: 02weight.html
Database name: swissmetro
Example of a logit model with three alternatives: Train, Car and Swissmetro. Weighted Exogenous Sample Maximum Likelihood estimator (WESML)

Estimation report

Number of estimated parameters: 4
Sample size: 6768
Excluded observations: 3960
Init log likelihood: -7016.87
Final log likelihood: -5273.743
Likelihood ratio test for the init. model: 3486.253
Rho-square for the init. model: 0.248
Rho-square-bar for the init. model: 0.248
Akaike Information Criterion: 10555.49
Bayesian Information Criterion: 10582.77
Final gradient norm: 2.1442E-02
Nbr of threads: 36
Algorithm: BFGS with trust region for simple bound constraints
Proportion analytical hessian: 0.0%
Relative projected gradient: 2.329406e-06
Number of iterations: 20
Number of function evaluations: 61
Number of gradient evaluations: 21
Number of hessian evaluations: 0
Cause of termination: Relative gradient = 2.3e-06 <= 6.1e-06
Optimization time: 0:00:00.110254

Estimated parameters

NameValueStd errt-testp-valueRob. Std errRob. t-testRob. p-value

Correlation of coefficients

Coefficient1Coefficient2CovarianceCorrelationt-testp-valueRob. cov.Rob. corr.Rob. t-testRob. p-value

Smallest eigenvalue: 156.927

Largest eigenvalue: 1501.27

Condition number: 9.56668