Model run by trashe using Apollo 0.4.0 on R 4.5.3 for Linux. Please acknowledge the use of Apollo by citing Hess & Palma (2019) DOI 10.1016/j.jocm.2019.100170 www.ApolloChoiceModelling.com Model name : FNL_grouped_shares Model description : Fractional NL model on mode choice SP data grouped by scenario, with shares weighted by the number of observations Model run at : 2026-11-02 22:16:09 Estimation method : bgw Estimation diagnosis : Relative function convergence (favorable) Optimisation diagnosis : Maximum found hessian properties : Negative definite maximum eigenvalue : -4.155529 reciprocal of condition number : 3.70525e-08 Number of individuals : 1322 Number of rows in database : 1322 Number of modelled outcomes : 1322 Sum of weights : 7000 (BIC uses the number of modelled outcomes) Number of cores used : 1 Model without mixing LL(start) : -8196.02 LL at equal shares, LL(0) : -8196.02 LL at observed shares, LL(C) : Not applicable LL(final) : -5586.14 Rho-squared vs equal shares : 0.3184 Adj.Rho-squared vs equal shares : 0.317 Rho-squared vs observed shares : Not applicable Adj.Rho-squared vs observed shares : Not applicable AIC : 11196.29 BIC : 11258.53 Estimated parameters : 12 Time taken (hh:mm:ss) : 00:00:1.17 pre-estimation : 00:00:0.51 estimation : 00:00:0.16 post-estimation : 00:00:0.49 Iterations : 14 Unconstrained optimisation. Estimates: Estimate s.e. t.rat.(0) t.rat(1) Rob.s.e. asc_car 0.000000 NA NA NA NA asc_bus -0.080048 0.465538 -0.1719 -2.320 0.487525 asc_air 0.172494 0.332282 0.5191 -2.490 0.349966 asc_rail -1.470257 0.317976 -4.6238 -7.769 0.347960 b_tt_car -0.011279 6.4982e-04 -17.3571 -1556.254 7.2366e-04 b_tt_bus -0.015660 0.001269 -12.3400 -800.343 0.001315 b_tt_air -0.018650 0.002554 -7.3029 -398.869 0.002679 b_tt_rail -0.005942 0.001642 -3.6181 -612.530 0.001771 b_access -0.021548 0.002581 -8.3492 -395.818 0.002610 b_cost -0.056983 0.001491 -38.2137 -708.829 0.001606 b_no_frills 0.000000 NA NA NA NA b_wifi 0.895371 0.052169 17.1630 -2.006 0.057371 b_food 0.385820 0.050526 7.6360 -12.156 0.054969 lambda_PT 0.762042 0.041580 18.3271 -5.723 0.040049 Rob.t.rat.(0) Rob.t.rat.(1) asc_car NA NA asc_bus -0.1642 -2.215 asc_air 0.4929 -2.365 asc_rail -4.2254 -7.099 b_tt_car -15.5860 -1397.456 b_tt_bus -11.9068 -772.247 b_tt_air -6.9613 -380.215 b_tt_rail -3.3555 -568.077 b_access -8.2572 -391.454 b_cost -35.4709 -657.952 b_no_frills NA NA b_wifi 15.6066 -1.824 b_food 7.0189 -11.173 lambda_PT 19.0276 -5.942 Nesting structure for FNL model component : Nest: root (1) |----Alternative: car |----Alternative: air '-Nest: PT (0.762) |-Alternative: bus '-Alternative: rail Overview of choices for FNL model component : car bus air rail Times available 832.00 978.00 837.00 946.00 Observations with non-zero share 658.00 254.00 543.00 786.00 Average share overall 0.29 0.07 0.23 0.41 Average share when available 0.45 0.09 0.37 0.58 Classical covariance matrix: asc_bus asc_air asc_rail b_tt_car b_tt_bus asc_bus 0.216725 0.035851 0.028250 9.713e-05 -5.1346e-04 asc_air 0.035851 0.110411 0.047686 1.2882e-04 2.176e-05 asc_rail 0.028250 0.047686 0.101109 1.3520e-04 4.030e-05 b_tt_car 9.713e-05 1.2882e-04 1.3520e-04 4.223e-07 1.216e-07 b_tt_bus -5.1346e-04 2.176e-05 4.030e-05 1.216e-07 1.610e-06 b_tt_air -3.606e-05 -6.0194e-04 -2.597e-05 -4.666e-08 7.286e-08 b_tt_rail 2.373e-05 1.863e-05 -3.9317e-04 -3.933e-08 -4.063e-08 b_access -5.738e-05 -4.7923e-04 -2.344e-05 1.351e-09 5.246e-08 b_cost 5.452e-06 -7.749e-05 -3.238e-05 2.573e-07 3.844e-07 b_wifi 1.390e-05 -0.002164 -0.001470 -6.067e-06 -8.205e-06 b_food -1.0746e-04 -0.001275 -0.001471 -3.158e-06 -3.845e-06 lambda_PT 0.001130 7.3709e-04 -1.305e-05 -2.819e-06 -1.329e-05 b_tt_air b_tt_rail b_access b_cost b_wifi asc_bus -3.606e-05 2.373e-05 -5.738e-05 5.452e-06 1.390e-05 asc_air -6.0194e-04 1.863e-05 -4.7923e-04 -7.749e-05 -0.002164 asc_rail -2.597e-05 -3.9317e-04 -2.344e-05 -3.238e-05 -0.001470 b_tt_car -4.666e-08 -3.933e-08 1.351e-09 2.573e-07 -6.067e-06 b_tt_bus 7.286e-08 -4.063e-08 5.246e-08 3.844e-07 -8.205e-06 b_tt_air 6.522e-06 -2.306e-07 2.147e-06 8.913e-07 -3.902e-06 b_tt_rail -2.306e-07 2.697e-06 -5.912e-07 5.317e-07 -9.649e-06 b_access 2.147e-06 -5.912e-07 6.661e-06 6.370e-07 -5.535e-06 b_cost 8.913e-07 5.317e-07 6.370e-07 2.224e-06 -2.018e-05 b_wifi -3.902e-06 -9.649e-06 -5.535e-06 -2.018e-05 0.002722 b_food -5.704e-06 -3.904e-06 -5.216e-06 -1.172e-05 0.001454 lambda_PT -8.185e-06 -3.736e-06 -1.594e-05 -1.623e-05 3.9385e-04 b_food lambda_PT asc_bus -1.0746e-04 0.001130 asc_air -0.001275 7.3709e-04 asc_rail -0.001471 -1.305e-05 b_tt_car -3.158e-06 -2.819e-06 b_tt_bus -3.845e-06 -1.329e-05 b_tt_air -5.704e-06 -8.185e-06 b_tt_rail -3.904e-06 -3.736e-06 b_access -5.216e-06 -1.594e-05 b_cost -1.172e-05 -1.623e-05 b_wifi 0.001454 3.9385e-04 b_food 0.002553 2.1980e-04 lambda_PT 2.1980e-04 0.001729 Robust covariance matrix: asc_bus asc_air asc_rail b_tt_car b_tt_bus asc_bus 0.237681 0.047976 0.041525 1.1924e-04 -5.4330e-04 asc_air 0.047976 0.122476 0.059084 1.5418e-04 1.789e-05 asc_rail 0.041525 0.059084 0.121077 1.6852e-04 3.474e-05 b_tt_car 1.1924e-04 1.5418e-04 1.6852e-04 5.237e-07 1.679e-07 b_tt_bus -5.4330e-04 1.789e-05 3.474e-05 1.679e-07 1.730e-06 b_tt_air -6.429e-05 -6.4483e-04 -3.226e-05 2.514e-08 1.996e-07 b_tt_rail -1.275e-05 -4.037e-06 -4.5992e-04 -5.525e-08 7.501e-08 b_access -1.1505e-04 -5.0698e-04 -3.488e-05 -3.792e-08 1.642e-07 b_cost 5.272e-05 -6.324e-05 -5.423e-05 3.353e-07 3.588e-07 b_wifi -0.001563 -0.003084 -0.001225 -7.414e-06 -5.747e-06 b_food 8.2483e-04 -0.001370 -7.7329e-04 -3.128e-06 -7.414e-06 lambda_PT 0.001187 -1.2126e-04 -7.4867e-04 -4.825e-06 -1.506e-05 b_tt_air b_tt_rail b_access b_cost b_wifi asc_bus -6.429e-05 -1.275e-05 -1.1505e-04 5.272e-05 -0.001563 asc_air -6.4483e-04 -4.037e-06 -5.0698e-04 -6.324e-05 -0.003084 asc_rail -3.226e-05 -4.5992e-04 -3.488e-05 -5.423e-05 -0.001225 b_tt_car 2.514e-08 -5.525e-08 -3.792e-08 3.353e-07 -7.414e-06 b_tt_bus 1.996e-07 7.501e-08 1.642e-07 3.588e-07 -5.747e-06 b_tt_air 7.178e-06 -5.144e-08 2.418e-06 9.908e-07 -1.241e-06 b_tt_rail -5.144e-08 3.136e-06 -5.847e-07 8.623e-07 -1.655e-05 b_access 2.418e-06 -5.847e-07 6.810e-06 5.672e-07 -1.265e-05 b_cost 9.908e-07 8.623e-07 5.672e-07 2.581e-06 -1.899e-05 b_wifi -1.241e-06 -1.655e-05 -1.265e-05 -1.899e-05 0.003291 b_food -8.954e-06 -1.112e-05 -3.774e-06 -1.357e-05 0.001837 lambda_PT -4.890e-06 -2.899e-06 -1.779e-05 -1.640e-05 5.0257e-04 b_food lambda_PT asc_bus 8.2483e-04 0.001187 asc_air -0.001370 -1.2126e-04 asc_rail -7.7329e-04 -7.4867e-04 b_tt_car -3.128e-06 -4.825e-06 b_tt_bus -7.414e-06 -1.506e-05 b_tt_air -8.954e-06 -4.890e-06 b_tt_rail -1.112e-05 -2.899e-06 b_access -3.774e-06 -1.779e-05 b_cost -1.357e-05 -1.640e-05 b_wifi 0.001837 5.0257e-04 b_food 0.003022 3.2753e-04 lambda_PT 3.2753e-04 0.001604 Classical correlation matrix: asc_bus asc_air asc_rail b_tt_car b_tt_bus asc_bus 1.000000 0.23176 0.19084 0.32109 -0.86911 asc_air 0.231762 1.00000 0.45132 0.59662 0.05160 asc_rail 0.190843 0.45132 1.00000 0.65433 0.09986 b_tt_car 0.321091 0.59662 0.65433 1.00000 0.14751 b_tt_bus -0.869114 0.05160 0.09986 0.14751 1.00000 b_tt_air -0.030334 -0.70934 -0.03198 -0.02812 0.02248 b_tt_rail 0.031034 0.03413 -0.75291 -0.03685 -0.01950 b_access -0.047758 -0.55882 -0.02856 8.0541e-04 0.01602 b_cost 0.007853 -0.15639 -0.06830 0.26549 0.20313 b_wifi 5.7218e-04 -0.12483 -0.08864 -0.17898 -0.12394 b_food -0.004568 -0.07594 -0.09153 -0.09618 -0.05997 lambda_PT 0.058374 0.05335 -9.8736e-04 -0.10434 -0.25195 b_tt_air b_tt_rail b_access b_cost b_wifi asc_bus -0.03033 0.03103 -0.04776 0.007853 5.7218e-04 asc_air -0.70934 0.03413 -0.55882 -0.156389 -0.12483 asc_rail -0.03198 -0.75291 -0.02856 -0.068300 -0.08864 b_tt_car -0.02812 -0.03685 8.0541e-04 0.265488 -0.17898 b_tt_bus 0.02248 -0.01950 0.01602 0.203132 -0.12394 b_tt_air 1.00000 -0.05498 0.32572 0.234051 -0.02928 b_tt_rail -0.05498 1.00000 -0.13949 0.217130 -0.11262 b_access 0.32572 -0.13949 1.00000 0.165513 -0.04111 b_cost 0.23405 0.21713 0.16551 1.000000 -0.25937 b_wifi -0.02928 -0.11262 -0.04111 -0.259367 1.00000 b_food -0.04421 -0.04705 -0.04000 -0.155492 0.55148 lambda_PT -0.07708 -0.05471 -0.14857 -0.261751 0.18157 b_food lambda_PT asc_bus -0.004568 0.05837 asc_air -0.075942 0.05335 asc_rail -0.091528 -9.8736e-04 b_tt_car -0.096179 -0.10434 b_tt_bus -0.059970 -0.25195 b_tt_air -0.044206 -0.07708 b_tt_rail -0.047054 -0.05471 b_access -0.039997 -0.14857 b_cost -0.155492 -0.26175 b_wifi 0.551481 0.18157 b_food 1.000000 0.10462 lambda_PT 0.104622 1.00000 Robust correlation matrix: asc_bus asc_air asc_rail b_tt_car b_tt_bus asc_bus 1.00000 0.281192 0.24478 0.33799 -0.84732 asc_air 0.28119 1.000000 0.48520 0.60878 0.03887 asc_rail 0.24478 0.485196 1.00000 0.66925 0.07591 b_tt_car 0.33799 0.608776 0.66925 1.00000 0.17636 b_tt_bus -0.84732 0.038867 0.07591 0.17636 1.00000 b_tt_air -0.04922 -0.687743 -0.03460 0.01297 0.05664 b_tt_rail -0.01477 -0.006514 -0.74642 -0.04312 0.03221 b_access -0.09043 -0.555120 -0.03842 -0.02008 0.04784 b_cost 0.06731 -0.112480 -0.09702 0.28846 0.16983 b_wifi -0.05588 -0.153615 -0.06135 -0.17857 -0.07617 b_food 0.03078 -0.071194 -0.04043 -0.07862 -0.10256 lambda_PT 0.06078 -0.008652 -0.05372 -0.16648 -0.28590 b_tt_air b_tt_rail b_access b_cost b_wifi asc_bus -0.049225 -0.014772 -0.09043 0.06731 -0.055881 asc_air -0.687743 -0.006514 -0.55512 -0.11248 -0.153615 asc_rail -0.034603 -0.746422 -0.03842 -0.09702 -0.061345 b_tt_car 0.012967 -0.043117 -0.02008 0.28846 -0.178571 b_tt_bus 0.056642 0.032207 0.04784 0.16983 -0.076171 b_tt_air 1.000000 -0.010843 0.34583 0.23021 -0.008075 b_tt_rail -0.010843 1.000000 -0.12653 0.30312 -0.162899 b_access 0.345831 -0.126530 1.00000 0.13529 -0.084500 b_cost 0.230206 0.303118 0.13529 1.00000 -0.206060 b_wifi -0.008075 -0.162899 -0.08450 -0.20606 1.000000 b_food -0.060799 -0.114223 -0.02631 -0.15364 0.582621 lambda_PT -0.045575 -0.040871 -0.17021 -0.25495 0.218727 b_food lambda_PT asc_bus 0.03078 0.060785 asc_air -0.07119 -0.008652 asc_rail -0.04043 -0.053723 b_tt_car -0.07862 -0.166476 b_tt_bus -0.10256 -0.285900 b_tt_air -0.06080 -0.045575 b_tt_rail -0.11422 -0.040871 b_access -0.02631 -0.170215 b_cost -0.15364 -0.254947 b_wifi 0.58262 0.218727 b_food 1.00000 0.148778 lambda_PT 0.14878 1.000000 Settings and functions used in model definition: apollo_control -------------- Value modelName "FNL_grouped_shares" modelDescr "Fractional NL model on mode choice SP data grouped by scenario, with shares weighted by the number of observations" indivID "scenario" weights "n_obs" outputDirectory "output/" debug "FALSE" nCores "1" workInLogs "FALSE" seed "13" mixing "FALSE" HB "FALSE" noValidation "FALSE" noDiagnostics "FALSE" calculateLLC "TRUE" analyticHessian "FALSE" dropLoopExpansion "FALSE" dropRedefCheck "FALSE" panelData "FALSE" analyticGrad "TRUE" analyticGrad_manualSet "FALSE" overridePanel "FALSE" preventOverridePanel "FALSE" noModification "FALSE" Hessian routines attempted -------------------------- numerical jacobian of LL analytical gradient apollo_probabilities ---------------------- function (apollo_beta, apollo_inputs, functionality = "estimate") { apollo_attach(apollo_beta, apollo_inputs) on.exit(apollo_detach(apollo_beta, apollo_inputs)) P = list() V = list() V[["car"]] = asc_car + b_tt_car * time_car + b_cost * cost_car V[["bus"]] = asc_bus + b_tt_bus * time_bus + b_access * access_bus + b_cost * cost_bus V[["air"]] = asc_air + b_tt_air * time_air + b_access * access_air + b_cost * cost_air + b_no_frills * (service_air == 1) + b_wifi * (service_air == 2) + b_food * (service_air == 3) V[["rail"]] = asc_rail + b_tt_rail * time_rail + b_access * access_rail + b_cost * cost_rail + b_no_frills * (service_rail == 1) + b_wifi * (service_rail == 2) + b_food * (service_rail == 3) nlNests = list(root = 1, PT = lambda_PT) nlStructure = list() nlStructure[["root"]] = c("car", "air", "PT") nlStructure[["PT"]] = c("bus", "rail") fnl_settings = list(alternatives = c("car", "bus", "air", "rail"), avail = list(car = av_car, bus = av_bus, air = av_air, rail = av_rail), choiceShares = list(car = share_car, bus = share_bus, air = share_air, rail = share_rail), utilities = V, nlNests = nlNests, nlStructure = nlStructure) P[["model"]] = apollo_fnl(fnl_settings, functionality) P = apollo_weighting(P, apollo_inputs, functionality) P = apollo_prepareProb(P, apollo_inputs, functionality) return(P) }