Mixture of logit with Halton drawsΒΆ

Example of a mixture of logit models, using quasi Monte-Carlo integration with Halton draws (base 5). The mixing distribution is normal.

Michel Bierlaire, EPFL Sat Jun 28 2025, 12:45:21

import biogeme.biogeme_logging as blog
from IPython.core.display_functions import display
from biogeme.biogeme import BIOGEME
from biogeme.expressions import Beta, Draws, MonteCarlo, log
from biogeme.models import logit
from biogeme.results_processing import get_pandas_estimated_parameters

See the data processing script: Data preparation for Swissmetro.

from swissmetro_data import (
    CAR_AV_SP,
    CAR_CO_SCALED,
    CAR_TT_SCALED,
    CHOICE,
    SM_AV,
    SM_COST_SCALED,
    SM_TT_SCALED,
    TRAIN_AV_SP,
    TRAIN_COST_SCALED,
    TRAIN_TT_SCALED,
    database,
)

logger = blog.get_screen_logger(level=blog.INFO)
logger.info('Example b24halton_mixture.py')
Example b24halton_mixture.py

Parameters to be estimated.

asc_car = Beta('asc_car', 0, None, None, 0)
asc_train = Beta('asc_train', 0, None, None, 0)
asc_sm = Beta('asc_sm', 0, None, None, 1)
b_cost = Beta('b_cost', 0, None, None, 0)

Define a random parameter, normally distributed, designed to be used for Monte-Carlo simulation.

b_time = Beta('b_time', 0, None, None, 0)

It is advised not to use 0 as starting value for the following parameter.

b_time_s = Beta('b_time_s', 1, None, None, 0)

Define a random parameter with a normal distribution, designed to be used for quasi Monte-Carlo simulation with Halton draws (base 5).

b_time_rnd = b_time + b_time_s * Draws('b_time_rnd', 'NORMAL_HALTON5')

Definition of the utility functions.

v_train = asc_train + b_time_rnd * TRAIN_TT_SCALED + b_cost * TRAIN_COST_SCALED
v_swissmetro = asc_sm + b_time_rnd * SM_TT_SCALED + b_cost * SM_COST_SCALED
v_car = asc_car + b_time_rnd * CAR_TT_SCALED + b_cost * CAR_CO_SCALED

Associate utility functions with the numbering of alternatives.

v = {1: v_train, 2: v_swissmetro, 3: v_car}

Associate the availability conditions with the alternatives.

av = {1: TRAIN_AV_SP, 2: SM_AV, 3: CAR_AV_SP}

Conditional on b_time_rnd, we have a logit model (called the kernel)

conditional_probability = logit(v, av, CHOICE)

We integrate over b_time_rnd using Monte-Carlo.

log_probability = log(MonteCarlo(conditional_probability))

These notes will be included as such in the report file.

USER_NOTES = (
    'Example of a mixture of logit models with three alternatives, '
    'approximated using Monte-Carlo integration with Halton draws.'
)

As the objective is to illustrate the syntax, we calculate the Monte-Carlo approximation with a small number of draws.

the_biogeme = BIOGEME(
    database, log_probability, user_notes=USER_NOTES, number_of_draws=10_000, seed=1223
)
the_biogeme.model_name = 'b24halton_mixture'
Biogeme parameters read from biogeme.toml.

Estimate the parameters

results = the_biogeme.estimate()
*** Initial values of the parameters are obtained from the file __b24halton_mixture.iter
Parameter values restored from __b24halton_mixture.iter
Starting values for the algorithm: {'asc_train': -0.40195185364181046, 'b_time': -2.2595838469305267, 'b_time_s': 1.6573078631733604, 'b_cost': -1.2852992156480805, 'asc_car': 0.1370262574783267}
As the model is rather complex, we cancel the calculation of second derivatives. If you want to control the parameters, change the algorithm from "automatic" to "simple_bounds" in the TOML file.
Optimization algorithm: hybrid Newton/BFGS with simple bounds [simple_bounds]
** Optimization: BFGS with trust region for simple bounds
Iter.       asc_train          b_time        b_time_s          b_cost         asc_car     Function    Relgrad   Radius      Rho
    0            -0.4            -2.3             1.7            -1.3            0.14      5.2e+03      7e-06    0.018 -8.5e+02    -
    1            -0.4            -2.3             1.7            -1.3            0.14      5.2e+03      7e-06   0.0091 -4.3e+02    -
    2            -0.4            -2.3             1.7            -1.3            0.14      5.2e+03      7e-06   0.0045 -1.8e+02    -
    3            -0.4            -2.3             1.7            -1.3            0.14      5.2e+03      7e-06   0.0023      -76    -
    4            -0.4            -2.3             1.7            -1.3            0.14      5.2e+03      7e-06   0.0011      -35    -
    5            -0.4            -2.3             1.7            -1.3            0.14      5.2e+03      7e-06  0.00057      -17    -
    6            -0.4            -2.3             1.7            -1.3            0.14      5.2e+03      7e-06  0.00028     -7.6    -
    7            -0.4            -2.3             1.7            -1.3            0.14      5.2e+03      7e-06  0.00014     -3.3    -
    8            -0.4            -2.3             1.7            -1.3            0.14      5.2e+03      7e-06  7.1e-05     -1.1    -
    9            -0.4            -2.3             1.7            -1.3            0.14      5.2e+03      7e-06  3.6e-05   -0.065    -
   10            -0.4            -2.3             1.7            -1.3            0.14      5.2e+03    4.4e-06  3.6e-05     0.47    -
Optimization algorithm has converged.
Relative gradient: 4.391778983297403e-06
Cause of termination: Relative gradient = 4.4e-06 <= 6.1e-06
Number of function evaluations: 14
Number of gradient evaluations: 3
Number of hessian evaluations: 0
Algorithm: BFGS with trust region for simple bound constraints
Number of iterations: 11
Proportion of Hessian calculation: 0/1 = 0.0%
Optimization time: 0:00:28.744647
Calculate second derivatives and BHHH
File b24halton_mixture~00.html has been generated.
File b24halton_mixture~00.yaml has been generated.
print(results.short_summary())
Results for model b24halton_mixture
Nbr of parameters:              5
Sample size:                    6768
Excluded data:                  3960
Final log likelihood:           -5214.905
Akaike Information Criterion:   10439.81
Bayesian Information Criterion: 10473.91
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 -0.401916         0.065838       -6.104587    1.030669e-09
1     b_time -2.259619         0.117085      -19.299005    0.000000e+00
2   b_time_s  1.657343         0.131714       12.582927    0.000000e+00
3     b_cost -1.285264         0.086295      -14.893876    0.000000e+00
4    asc_car  0.136991         0.051721        2.648645    8.081517e-03

Total running time of the script: (2 minutes 32.643 seconds)

Gallery generated by Sphinx-Gallery