Mixtures of logit with Monte-Carlo 10_000 Halton draws

Estimation of a mixtures of logit models where the integral is approximated using MonteCarlo integration with Halton draws.

Michel Bierlaire, EPFL Tue Apr 29 2025, 12:15:53

from b07estimation_specification import get_biogeme
from IPython.core.display_functions import display

import biogeme.biogeme_logging as blog
from biogeme.expressions import Draws
from biogeme.results_processing import (
    EstimationResults,
    get_pandas_estimated_parameters,
)

logger = blog.get_screen_logger(level=blog.INFO)
logger.info('Example b07estimation_monte_carlo_halton.py')

Example b07estimation_monte_carlo_halton.py

R = 10_000

the_draws = Draws('b_time_rnd', 'NORMAL_HALTON2')
the_biogeme = get_biogeme(the_draws=the_draws, number_of_draws=R)
the_biogeme.model_name = 'b07estimation_monte_carlo_halton'
results_file = f'saved_results/{the_biogeme.model_name}.yaml'

Biogeme parameters read from biogeme.toml.

try:
    results = EstimationResults.from_yaml_file(filename=results_file)
except FileNotFoundError:
    results = the_biogeme.estimate()

print(results.short_summary())

Results for model b07estimation_monte_carlo_halton
Nbr of parameters:              5
Sample size:                    10719
Excluded data:                  9
Final log likelihood:           -8570.985
Akaike Information Criterion:   17151.97
Bayesian Information Criterion: 17188.37

Get the results in a pandas table

pandas_results = get_pandas_estimated_parameters(
    estimation_results=results,
)
display(pandas_results)

        Name     Value  Robust std err.  Robust t-stat.  Robust p-value
0  asc_train -0.467353         0.047971       -9.742337    0.000000e+00
1     b_time -1.863180         0.075890      -24.551114    0.000000e+00
2   b_time_s  1.207743         0.087394       13.819538    0.000000e+00
3     b_cost -0.845652         0.057675      -14.662369    0.000000e+00
4    asc_car  0.180178         0.035154        5.125463    2.968073e-07