biogeme 2.5 [Dim 19 jui 2016 17:58:58 CEST]
Michel Bierlaire, EPFL
This file has automatically been generated.
Thu Jul 7 17:54:46 2016
Tip: click on the columns headers to sort a table [Credits]
|
Example of a Network GEV model. It is actually a cross nested logit model for a transportation mode choice with 3 alternatives:
|
|
- Train
|
|
- Car
|
|
- Swissmetro, an hypothetical high-speed train
|
|
We introduce a nest called EXISTING involving Car and Train
|
|
and a nest called PUBLIC involving Swissmetro and Train
|
|
Note that the alternative Train belongs to the two nests.
|
|
It is the same model as 11cnl.mod.
|
| Model: | Network GEV model |
| Number of estimated parameters: | 8 |
| Number of observations: | 6768 |
| Number of individuals: | 6768 |
| Null log likelihood: | -6964.663 |
| Init log likelihood: | -6964.663 |
| Final log likelihood: | -5214.049 |
| Likelihood ratio test: | 3501.228 |
| Rho-square: | 0.251 |
| Adjusted rho-square: | 0.250 |
| Final gradient norm: | +2.100e-04 |
| Diagnostic: | Normal termination. Obj: 6.05545e-06 Const: 6.05545e-06 |
| Iterations: | 35 |
| Run time: | 00:16 |
| Variance-covariance: | from finite difference hessian |
| Sample file: | ../swissmetro.dat |
Utility parameters
| Name | Value | Std err | t-test | p-value | |
|---|
| ASC_CAR | -0.240 | 0.0384 | -6.26 | 0.00 | | | | | |
| ASC_SM | 0.00 | fixed | | | | | | | |
| ASC_TRAIN | -0.381 | 0.0492 | -7.74 | 0.00 | | | | | |
| B_COST | -0.819 | 0.0446 | -18.36 | 0.00 | | | | | |
| B_TIME | -0.777 | 0.0558 | -13.93 | 0.00 | | | | | |
Model parameters
| Name | Value | Std err | t-test 0 | p-value | t-test 1 | p-value | | Robust Std err | Robust t-test 0 | p-value | Robust t-test 1 | p-value | |
|---|
| A1_TRAIN | 1.00 | fixed | | | | | | | | | | | |
| A2_SM | 1.00 | fixed | | | | | | | | | | | |
| A3_Car | 1.00 | fixed | | | | | | | | | | | |
| EXISTING | 2.51 | 0.175 | 14.40 | 0.00 | 8.68 | 0.00 | | | | | | | |
| PUBLIC | 4.11 | 0.569 | 7.23 | 0.00 | 5.48 | 0.00 | | | | | | | |
| EXISTING_A1_TRAIN | 0.569 | 0.0865 | 6.57 | 0.00 | -4.98 | 0.00 | | | | | | | |
| EXISTING_A3_Car | 1.00 | fixed | | | | | | | | | | | |
| PUBLIC_A1_TRAIN | 0.431 | 0.0865 | 4.98 | 0.00 | -6.57 | 0.00 | | | | | | | |
| PUBLIC_A2_SM | 1.00 | fixed | | | | | | | | | | | |
| __ROOT_EXISTING | 1.00 | fixed | | | | | | | | | | | |
| __ROOT_PUBLIC | 1.00 | fixed | | | | | | | | | | | |
Utility functions
| Id | Name | Availability | Specification |
|---|
| 1 | A1_TRAIN | TRAIN_AV_SP | ASC_TRAIN * one + B_TIME * TRAIN_TT_SCALED + B_COST * TRAIN_COST_SCALED |
| 2 | A2_SM | SM_AV | ASC_SM * one + B_TIME * SM_TT_SCALED + B_COST * SM_COST_SCALED |
| 3 | A3_Car | CAR_AV_SP | ASC_CAR * one + B_TIME * CAR_TT_SCALED + B_COST * CAR_CO_SCALED |
Correlation of coefficients
| Coefficient1 | Coefficient2 | Covariance | Correlation | t-test | p-value | | Rob. cov. | Rob. corr. | Rob. t-test | p-value | |
|---|
|
ASC_CAR | ASC_TRAIN | 0.000647 | 0.343 | 2.75 | 0.01 | | |
|
ASC_CAR | B_COST | -0.000103 | -0.0601 | 9.54 | 0.00 | | |
|
ASC_CAR | B_TIME | -0.00132 | -0.614 | 6.31 | 0.00 | | |
|
ASC_TRAIN | B_COST | 0.000711 | 0.324 | 8.02 | 0.00 | | |
|
ASC_TRAIN | B_TIME | -0.000637 | -0.232 | 4.81 | 0.00 | | |
|
B_COST | B_TIME | 0.00115 | 0.460 | -0.79 | 0.43 | * | |
User defined linear constraints
1*EXISTING_A1_TRAIN + 1*PUBLIC_A1_TRAIN = 1 [1 = 1]
Smallest singular value of the hessian: 0.837813