22: MTC Motorized and Non-Motorized Nested Mode Choice¶

import larch.numba as lx
m = lx.example(17)

For this example, we’re going to re-create model 22 from the Self Instructing Manual. (pp. 179)

motorized = m.graph.new_node(parameter='mu_motor', children=[1,2,3,4], name='Motorized')
nonmotorized = m.graph.new_node(parameter='mu_nonmotor', children=[5,6], name='Nonmotorized')

m.ordering = (
    ("CostbyInc","costbyincome",),
    ("TravelTime",".*time.*",".*dist.*", ),
    ("Household","hhinc.*","vehbywrk.*",),
    ("Zonal","wkcbd.*","wkempden.*",),
    ("ASCs","ASC.*",),
)

m.loglike()

-7309.600971749634

m.maximize_loglike()

/home/runner/work/larch/larch/larch/larch/model/optimization.py:308: UserWarning: slsqp may not play nicely with unbounded parameters
if you get poor results, consider setting global bounds with model.set_cap()
  warnings.warn( # infinite bounds # )

key

value

x

	0
ASC_Bike	-1.201
ASC_SR2	-1.325
ASC_SR3+	-2.506
ASC_Transit	-0.404
ASC_Walk	0.345
costbyincome	-0.039
hhinc#4	-0.004
hhinc#5	-0.010
hhinc#6	-0.006
motorized_ovtbydist	-0.114
motorized_time	-0.015
mu_motor	0.726
mu_nonmotor	0.769
nonmotorized_time	-0.046
vehbywrk_Bike	-0.735
vehbywrk_SR	-0.226
vehbywrk_Transit	-0.707
vehbywrk_Walk	-0.764
wkcbd_Bike	0.408
wkcbd_SR2	0.193
wkcbd_SR3+	0.781
wkcbd_Transit	0.921
wkcbd_Walk	0.114
wkempden_Bike	0.002
wkempden_SR2	0.001
wkempden_SR3+	0.002
wkempden_Transit	0.002
wkempden_Walk	0.002

loglike

-3441.672527117994

d_loglike

	0
ASC_Bike	5.979e-05
ASC_SR2	-2.561e-03
ASC_SR3+	-6.798e-04
ASC_Transit	-1.606e-03
ASC_Walk	-6.126e-05
costbyincome	-6.766e-03
hhinc#4	-1.077e-01
hhinc#5	1.052e-02
hhinc#6	-1.973e-02
motorized_ovtbydist	-1.108e-02
motorized_time	-7.640e-02
mu_motor	-1.422e-02
mu_nonmotor	-1.544e-04
nonmotorized_time	-6.179e-03
vehbywrk_Bike	-3.140e-05
vehbywrk_SR	-5.988e-03
vehbywrk_Transit	-1.010e-03
vehbywrk_Walk	-1.431e-05
wkcbd_Bike	2.391e-04
wkcbd_SR2	4.213e-04
wkcbd_SR3+	-4.595e-04
wkcbd_Transit	-6.164e-04
wkcbd_Walk	-6.433e-04
wkempden_Bike	2.838e-02
wkempden_SR2	-2.895e-02
wkempden_SR3+	-3.320e-01
wkempden_Transit	5.577e-01
wkempden_Walk	-1.504e-01

nit

71

nfev

195

njev

71

status

0

message

'Optimization terminated successfully'

success

True

elapsed_time

0:00:01.524991

method

'slsqp'

n_cases

5029

iteration_number

0

logloss

0.6843651873370439

__verbose_repr__

True

m.calculate_parameter_covariance()
m.parameter_summary()

		Value	Std Err	t Stat	Signif	Null Value
Category	Parameter
CostbyInc	costbyincome	-0.0386	0.0104	-3.72	***	0.00
TravelTime	motorized_time	-0.0145	0.00387	-3.76	***	0.00
	nonmotorized_time	-0.0462	0.00540	-8.56	***	0.00
	motorized_ovtbydist	-0.114	0.0211	-5.39	***	0.00
Household	hhinc#4	-0.00393	0.00161	-2.44	*	0.00
	hhinc#5	-0.0100	0.00465	-2.16	*	0.00
	hhinc#6	-0.00621	0.00302	-2.05	*	0.00
	vehbywrk_Bike	-0.735	0.229	-3.21	**	0.00
	vehbywrk_SR	-0.226	0.0651	-3.47	***	0.00
	vehbywrk_Transit	-0.707	0.150	-4.72	***	0.00
	vehbywrk_Walk	-0.764	0.163	-4.68	***	0.00
Zonal	wkcbd_Bike	0.408	0.328	1.24		0.00
	wkcbd_SR2	0.193	0.0962	2.01	*	0.00
	wkcbd_SR3+	0.781	0.200	3.91	***	0.00
	wkcbd_Transit	0.921	0.222	4.15	***	0.00
	wkcbd_Walk	0.114	0.236	0.48		0.00
	wkempden_Bike	0.00167	0.00109	1.54		0.00
	wkempden_SR2	0.00115	0.000354	3.24	**	0.00
	wkempden_SR3+	0.00164	0.000449	3.65	***	0.00
	wkempden_Transit	0.00224	0.000507	4.41	***	0.00
	wkempden_Walk	0.00217	0.000762	2.85	**	0.00
ASCs	ASC_Bike	-1.20	0.417	-2.88	**	0.00
	ASC_SR2	-1.33	0.255	-5.20	***	0.00
	ASC_SR3+	-2.51	0.475	-5.28	***	0.00
	ASC_Transit	-0.404	0.221	-1.82		0.00
	ASC_Walk	0.345	0.358	0.97		0.00
Other	mu_motor	0.726	0.135	-2.03	*	1.00
Other	mu_nonmotor	0.769	0.179	-1.29		1.00

v5.7.0

22: MTC Motorized and Non-Motorized Nested Mode Choice

22: MTC Motorized and Non-Motorized Nested Mode Choice¶