adeeba

Radeen10-_

May 16th, 2025

1,833

Never

Add comment

Not a member of Pastebin yet? Sign Up, it unlocks many cool features!

R 37.18 KB | None | 0 0

raw download clone embed print report

rm(list = ls())
library(apollo)
library(tidyverse)
library(dplyr)
library(psych)
library(utils)
library(fastDummies)
library(cutoff)
library(lavaan)
library(semPlot)
library(StatMatch)
library(semTools)
library(SciViews)
library(readxl)
# ─────────────────────────────────────────────────────────────────────────────
# 1. Data wrangling ---------------------------------------------------------
# ─────────────────────────────────────────────────────────────────────────────
data <- read_excel("D:/adeeba/Dataset_long.xlsx")
data <- data %>%
mutate(across(c(2, 4, 62, 63, 76, 79, 81, 83, 85, 88, 90, 182:186, 188,
222, 223), as.factor)) %>%
dummy_cols(
select_columns = c("marry_stat", "education", "student", "emp_stat",
"emp_arrange", "license", "hh_living_stat", "hh_years",
"personal_income", "family_income"),
remove_selected_columns = TRUE
) %>%
mutate(
edu_below_uni = education_1 + education_2,
student = student_3 + student_2,
employed = emp_stat_3 + emp_stat_4,
hybrid_worker = emp_arrange_3 + emp_arrange_4 + emp_arrange_5,
living_with_family = hh_living_stat_3 + hh_living_stat_4 + hh_living_stat_5,
hh_years_above_5 = hh_years_4 + hh_years_5,
personal_income_above_25k= personal_income_3 + personal_income_4 +
personal_income_5 + personal_income_6 +
personal_income_7 + personal_income_8,
personal_income_above_50k= personal_income_4 + personal_income_5 +
personal_income_6 + personal_income_7 +
personal_income_8,
family_income_above_50k = family_income_4 + family_income_5 +
family_income_6 + family_income_7 +
family_income_8 + family_income_9 +
family_income_10 + family_income_11,
family_income_above_100k = family_income_6 + family_income_7 +
family_income_8 + family_income_9 +
family_income_10 + family_income_11
)
database <- data
database$bus.crowd2 <- ifelse(database$bus.crowd == 2, 1, 0)
database$bus.crowd3 <- ifelse(database$bus.crowd == 3, 1, 0)
database$transit.crowd2 <- ifelse(database$transit.crowd == 2, 1, 0)
database$transit.crowd3 <- ifelse(database$transit.crowd == 3, 1, 0)
database$best <- case_when(
database$choice == "privatecar" ~ 1,
database$choice == "ubercar" ~ 2,
database$choice == "cng" ~ 3,
database$choice == "bike" ~ 4,
database$choice == "rickshaw" ~ 5,
database$choice == "bus" ~ 6,
database$choice == "transit" ~ 7
)
# remove any previously calculated LV columns that may exist
database <- database[ , !names(database) %in%
c("decisionoverload","hassle","knowledge",
"socialnorms","attmultimodality")]
# ─────────────────────────────────────────────────────────────────────────────
# 2. Apollo set-up ----------------------------------------------------------
# ─────────────────────────────────────────────────────────────────────────────
apollo_initialise()
apollo_control <- list(
modelName = "Congestion Mode Choice Model (ICLV_OL_500_orig spec)",
modelDescr = "Mixed Logit model with OL",
indivID = "id",
nCores = 4
)
apollo_beta = c(
### Alternative Specific Constants (ASC) – base case is PrivateCar
asc_pc = 0,
asc_ubercar = 0, # Ride-hailing car
asc_cng = 0, # Ride-hailing cng
asc_bike = 0, # Ride-hailing bike
asc_rickshaw = 0, # Rickshaw
asc_bus = 0, # Bus
asc_transit = 0, # Transit (MRT/BRT)
### Travel Time Coefficients
b_attc = -0.0591, # Average travel time for PrivateCar
b_attr = -0.0321, # Average travel time for Rickshaw
b_attb = -0.0351, # Average travel time for Bus
b_attt = -0.0600, # Average travel time for Transit
b_attbike = -0.0591, # Average travel time for RH bike
# Means of random parameters
mu_conttc = -0.006, # PrivateCar
mu_conttr = -0.008, # Rickshaw
mu_conttb = -0.015, # Bus
mu_conttt = -0.013, # Transit
mu_conttbike= -0.008, # RideHailingBike
mu_uncerc = -0.006, # PrivateCar
mu_uncerr = -0.010, # Rickshaw
mu_uncerb = -0.015, # Bus
mu_uncerbike= -0.006, # RideHailingBike
# Standard deviations of random parameters
sigma_conttc = 0.002,
sigma_conttr = 0.002,
sigma_conttb = 0.002,
sigma_conttt = 0.002,
sigma_conttbike= 0.002,
sigma_uncerc = 0.002,
sigma_uncerr = 0.002,
sigma_uncerb = 0.002,
sigma_uncerbike= 0.002,
### Cost
b_cost = -0.0107, # Cost (PrivateCar, Rickshaw, Bus, Transit)
b_parkfee = -0.03, # Parking fee – only for PrivateCar
### Wait Time and Walk Time
b_wait = -0.08, # Waiting time for Ride-hailing, Rickshaw, Transit, Bus
b_walk = -0.07, # Walking time for Bus and Transit
### Transfers
b_transfers = -0.5, # Number of transfers (Bus, Transit)
### Crowding
b_crowd_2 = -0.4, # Crowding level 1 (moderately crowded)
b_crowd_3 = -0.4, # Crowding level 2 (very crowded)
### Schedule Reliability
b_schedule = 0.4, # Schedule dummy = 1 if reliable (Bus and Transit)
### Park-and-Ride
b_pnr = 0.3, # PNR facility dummy – Transit only
### Grade-Separated Infrastructure
b_grade = 0.5, # Dummy: 1 if MRT (fully grade-separated Transit), Dummy: 0 if BRT
# MIMIC parameters
# Decision Overload
g_age_do = 1,
g_student_do = 1,
g_edu_below_uni_do = 1,
g_hh_years_above_5_do = 1,
g_personal_income_above_50k_do = 1,
g_family_income_above_50k_do = 1,
g_license_2_do = 1,
g_dissonant_user_do = 1,
g_pv_avail_number_do = 1,
g_commuting_mmi_do = 1,
g_passes_yes_do = 1,
# Hassle
g_age_hs = 1,
g_student_hs = 1,
g_edu_below_uni_hs = 1,
g_hh_years_above_5_hs = 1,
g_personal_income_above_50k_hs = 1,
g_family_income_above_50k_hs = 1,
g_license_2_hs = 1,
g_commuting_mmi_hs = 1,
g_marry_stat_1_hs = 1,
g_employed_hs = 1,
g_do_hs = 1, # linking latent variable decisionoverload to hassle
# Attitude toward Multimodality
g_age_att = 1,
g_edu_below_uni_att = 1,
g_family_income_above_50k_att= 1,
g_license_2_att = 1,
g_dissonant_user_att = 1,
g_marry_stat_1_att = 1,
g_gender_att = 1,
g_employed_att = 1,
g_pv_access_att = 1,
g_disabled_yes_att = 1,
g_employed_mm_view = 1,
# Social Norms
g_age_sn = 1,
g_student_sn = 1,
g_edu_below_uni_sn = 1,
g_hh_years_above_5_sn = 1,
g_family_income_above_50k_sn = 1,
g_license_2_sn = 1,
g_dissonant_user_sn = 1,
g_commuting_mmi_sn = 1,
g_marry_stat_1_sn = 1,
# Knowledge
g_age_ka = 1,
g_edu_below_uni_ka = 1,
g_hh_years_above_5_ka = 1,
g_license_2_ka = 1,
g_dissonant_user_ka = 1,
g_commuting_mmi_ka = 1,
g_gender_ka = 1,
# Measurement equations parameters
z_do4 = 1, z_do5 = 1,
z_ka1 = 1, z_ka2 = 1, z_ka3 = 1,
z_hs1 = 1, z_hs2 = 1, z_hs3 = 1, z_hs4 = 1, z_hs5 = 1, z_hs6 = 1, z_hs7 = 1,
z_att1= 1, z_att2= 1, z_att3= 1, z_att5= 1, z_att6= 1,
z_sn1 = 1, z_sn2 = 1, z_sn3 = 1,
# Decision Overload
tau_do4_1 = -2, tau_do4_2 = -1, tau_do4_3 = 1, tau_do4_4 = 2,
tau_do5_1 = -2, tau_do5_2 = -1, tau_do5_3 = 1, tau_do5_4 = 2,
# Knowledge Adequacy
tau_ka1_1 = -2, tau_ka1_2 = -1, tau_ka1_3 = 1, tau_ka1_4 = 2,
tau_ka2_1 = -2, tau_ka2_2 = -1, tau_ka2_3 = 1, tau_ka2_4 = 2,
tau_ka3_1 = -2, tau_ka3_2 = -1, tau_ka3_3 = 1, tau_ka3_4 = 2,
# Hassle
tau_hs1_1 = -2, tau_hs1_2 = -1, tau_hs1_3 = 1, tau_hs1_4 = 2,
tau_hs2_1 = -2, tau_hs2_2 = -1, tau_hs2_3 = 1, tau_hs2_4 = 2,
tau_hs3_1 = -2, tau_hs3_2 = -1, tau_hs3_3 = 1, tau_hs3_4 = 2,
tau_hs4_1 = -2, tau_hs4_2 = -1, tau_hs4_3 = 1, tau_hs4_4 = 2,
tau_hs5_1 = -2, tau_hs5_2 = -1, tau_hs5_3 = 1, tau_hs5_4 = 2,
tau_hs6_1 = -2, tau_hs6_2 = -1, tau_hs6_3 = 1, tau_hs6_4 = 2,
tau_hs7_1 = -2, tau_hs7_2 = -1, tau_hs7_3 = 1, tau_hs7_4 = 2,
# Attitude Toward Multimodality
tau_att1_1 = -2, tau_att1_2 = -1, tau_att1_3 = 1, tau_att1_4 = 2,
tau_att2_1 = -2, tau_att2_2 = -1, tau_att2_3 = 1, tau_att2_4 = 2,
tau_att3_1 = -2, tau_att3_2 = -1, tau_att3_3 = 1, tau_att3_4 = 2,
tau_att5_1 = -2, tau_att5_2 = -1, tau_att5_3 = 1, tau_att5_4 = 2,
tau_att6_1 = -2, tau_att6_2 = -1, tau_att6_3 = 1, tau_att6_4 = 2,
# Social Norms
tau_sn1_1 = -2, tau_sn1_2 = -1, tau_sn1_3 = 1, tau_sn1_4 = 2,
tau_sn2_1 = -2, tau_sn2_2 = -1, tau_sn2_3 = 1, tau_sn2_4 = 2,
tau_sn3_1 = -2, tau_sn3_2 = -1, tau_sn3_3 = 1, tau_sn3_4 = 2
)
apollo_fixed <- c() # nothing fixed
# ─────────────────────────────────────────────────────────────────────────────
# 3. Draws and random coefficients -----------------------------------------
# ─────────────────────────────────────────────────────────────────────────────
apollo_draws <- list(
interDrawsType = "halton",
interNDraws = 100,
interNormDraws = c("eta_do","eta_ka","eta_hs","eta_att","eta_sn",
"draws_conttc","draws_conttr","draws_conttb",
"draws_conttt","draws_conttbike",
"draws_uncerc","draws_uncerr","draws_uncerb",
"draws_uncerbike")
)
apollo_randCoeff <- function(apollo_beta, apollo_inputs){
rc <- list()
## random coefficients for travel-time congestion & uncertainty ----------
rc$b_conttc <- -exp(mu_conttc + sigma_conttc * draws_conttc)
rc$b_conttr <- -exp(mu_conttr + sigma_conttr * draws_conttr)
rc$b_conttb <- -exp(mu_conttb + sigma_conttb * draws_conttb)
rc$b_conttt <- -exp(mu_conttt + sigma_conttt * draws_conttt)
rc$b_conttbike <- -exp(mu_conttbike + sigma_conttbike * draws_conttbike)
rc$b_uncerc <- -exp(mu_uncerc + sigma_uncerc * draws_uncerc)
rc$b_uncerr <- -exp(mu_uncerr + sigma_uncerr * draws_uncerr)
rc$b_uncerb <- -exp(mu_uncerb + sigma_uncerb * draws_uncerb)
rc$b_uncerbike <- -exp(mu_uncerbike + sigma_uncerbike * draws_uncerbike)
## latent variables (MIMIC structure) --------------------------------------
rc$decisionoverload <- g_age_do*age + g_student_do*student + g_edu_below_uni_do*edu_below_uni +
g_hh_years_above_5_do*hh_years_above_5 +
g_personal_income_above_50k_do*personal_income_above_50k +
g_family_income_above_50k_do*family_income_above_50k +
g_license_2_do*license_2 + g_dissonant_user_do*dissonant_user +
g_pv_avail_number_do*pv_avail_number +
g_commuting_mmi_do*commuting_mmi +
g_passes_yes_do*passes_yes + eta_do
rc$hassle <- g_age_hs*age + g_student_hs*student + g_edu_below_uni_hs*edu_below_uni +
g_hh_years_above_5_hs*hh_years_above_5 +
g_personal_income_above_50k_hs*personal_income_above_50k +
g_family_income_above_50k_hs*family_income_above_50k +
g_license_2_hs*license_2 + g_commuting_mmi_hs*commuting_mmi +
g_marry_stat_1_hs*marry_stat_1 + g_employed_hs*employed +
g_do_hs*rc$decisionoverload + eta_hs
rc$attmultimodality <- g_age_att*age + g_edu_below_uni_att*edu_below_uni +
g_family_income_above_50k_att*family_income_above_50k +
g_license_2_att*license_2 + g_dissonant_user_att*dissonant_user +
g_marry_stat_1_att*marry_stat_1 + g_gender_att*gender +
g_employed_mm_view*employed + g_pv_access_att*pv_access +
g_disabled_yes_att*disabled_yes + eta_att
rc$socialnorms <- g_age_sn*age + g_student_sn*student + g_edu_below_uni_sn*edu_below_uni +
g_hh_years_above_5_sn*hh_years_above_5 +
g_family_income_above_50k_sn*family_income_above_50k +
g_license_2_sn*license_2 + g_dissonant_user_sn*dissonant_user +
g_commuting_mmi_sn*commuting_mmi + g_marry_stat_1_sn*marry_stat_1 +
eta_sn
rc$knowledge <- g_age_ka*age + g_edu_below_uni_ka*edu_below_uni +
g_hh_years_above_5_ka*hh_years_above_5 + g_license_2_ka*license_2 +
g_dissonant_user_ka*dissonant_user + g_commuting_mmi_ka*commuting_mmi +
g_gender_ka*gender + eta_ka
# export them as plain symbols for apollo_probabilities()
list2env(rc, parent.frame())
return(rc)
}
# ─────────────────────────────────────────────────────────────────────────────
# 4. Validate inputs --------------------------------------------------------
# ─────────────────────────────────────────────────────────────────────────────
apollo_inputs <- apollo_validateInputs()
# ─────────────────────────────────────────────────────────────────────────────
# 5. Likelihood function ----------------------------------------------------
# ─────────────────────────────────────────────────────────────────────────────
apollo_probabilities <- function(apollo_beta, apollo_inputs, functionality = "estimate"){
apollo_attach(apollo_beta, apollo_inputs)
on.exit(apollo_detach(apollo_beta, apollo_inputs))
P <- list()
## ordered-logit measurement models ---------------------------------------
P$do4 <- apollo_ol(list(outcomeOrdered = do4,
V = z_do4 * decisionoverload,
tau = list(tau_do4_1,tau_do4_2,tau_do4_3,tau_do4_4),
rows = (sp_scen == 1),
componentName="do4"), functionality)
P$do5 <- apollo_ol(list(outcomeOrdered = do5,
V = z_do5 * decisionoverload,
tau = list(tau_do5_1,tau_do5_2,tau_do5_3,tau_do5_4),
rows = (sp_scen == 1),
componentName="do5"), functionality)
P$hs1 <- apollo_ol(list(outcomeOrdered = hs1,
V = z_hs1 * hassle,
tau = list(tau_hs1_1,tau_hs1_2,tau_hs1_3,tau_hs1_4),
rows = (sp_scen == 1),
componentName="hs1"), functionality)
# … (repeat for hs2-hs7, ka1-ka3, sn1-sn3, att1-att6) … --------------------
P$hs2 <- apollo_ol(list(outcomeOrdered=hs2,V=z_hs2*hassle,
tau=list(tau_hs2_1,tau_hs2_2,tau_hs2_3,tau_hs2_4),
rows=(sp_scen==1),componentName="hs2"),functionality)
P$hs3 <- apollo_ol(list(outcomeOrdered=hs3,V=z_hs3*hassle,
tau=list(tau_hs3_1,tau_hs3_2,tau_hs3_3,tau_hs3_4),
rows=(sp_scen==1),componentName="hs3"),functionality)
P$hs4 <- apollo_ol(list(outcomeOrdered=hs4,V=z_hs4*hassle,
tau=list(tau_hs4_1,tau_hs4_2,tau_hs4_3,tau_hs4_4),
rows=(sp_scen==1),componentName="hs4"),functionality)
P$hs5 <- apollo_ol(list(outcomeOrdered=hs5,V=z_hs5*hassle,
tau=list(tau_hs5_1,tau_hs5_2,tau_hs5_3,tau_hs5_4),
rows=(sp_scen==1),componentName="hs5"),functionality)
P$hs6 <- apollo_ol(list(outcomeOrdered=hs6,V=z_hs6*hassle,
tau=list(tau_hs6_1,tau_hs6_2,tau_hs6_3,tau_hs6_4),
rows=(sp_scen==1),componentName="hs6"),functionality)
P$hs7 <- apollo_ol(list(outcomeOrdered=hs7,V=z_hs7*hassle,
tau=list(tau_hs7_1,tau_hs7_2,tau_hs7_3,tau_hs7_4),
rows=(sp_scen==1),componentName="hs7"),functionality)
P$ka1 <- apollo_ol(list(outcomeOrdered=ka1,V=z_ka1*knowledge,
tau=list(tau_ka1_1,tau_ka1_2,tau_ka1_3,tau_ka1_4),
rows=(sp_scen==1),componentName="ka1"),functionality)
P$ka2 <- apollo_ol(list(outcomeOrdered=ka2,V=z_ka2*knowledge,
tau=list(tau_ka2_1,tau_ka2_2,tau_ka2_3,tau_ka2_4),
rows=(sp_scen==1),componentName="ka2"),functionality)
P$ka3 <- apollo_ol(list(outcomeOrdered=ka3,V=z_ka3*knowledge,
tau=list(tau_ka3_1,tau_ka3_2,tau_ka3_3,tau_ka3_4),
rows=(sp_scen==1),componentName="ka3"),functionality)
P$sn1 <- apollo_ol(list(outcomeOrdered=sn1,V=z_sn1*socialnorms,
tau=list(tau_sn1_1,tau_sn1_2,tau_sn1_3,tau_sn1_4),
rows=(sp_scen==1),componentName="sn1"),functionality)
P$sn2 <- apollo_ol(list(outcomeOrdered=sn2,V=z_sn2*socialnorms,
tau=list(tau_sn2_1,tau_sn2_2,tau_sn2_3,tau_sn2_4),
rows=(sp_scen==1),componentName="sn2"),functionality)
P$sn3 <- apollo_ol(list(outcomeOrdered=sn3,V=z_sn3*socialnorms,
tau=list(tau_sn3_1,tau_sn3_2,tau_sn3_3,tau_sn3_4),
rows=(sp_scen==1),componentName="sn3"),functionality)
P$att1 <- apollo_ol(list(outcomeOrdered=att1,V=z_att1*attmultimodality,
tau=list(tau_att1_1,tau_att1_2,tau_att1_3,tau_att1_4),
rows=(sp_scen==1),componentName="att1"),functionality)
P$att2 <- apollo_ol(list(outcomeOrdered=att2,V=z_att2*attmultimodality,
tau=list(tau_att2_1,tau_att2_2,tau_att2_3,tau_att2_4),
rows=(sp_scen==1),componentName="att2"),functionality)
P$att3 <- apollo_ol(list(outcomeOrdered=att3,V=z_att3*attmultimodality,
tau=list(tau_att3_1,tau_att3_2,tau_att3_3,tau_att3_4),
rows=(sp_scen==1),componentName="att3"),functionality)
P$att5 <- apollo_ol(list(outcomeOrdered=att5,V=z_att5*attmultimodality,
tau=list(tau_att5_1,tau_att5_2,tau_att5_3,tau_att5_4),
rows=(sp_scen==1),componentName="att5"),functionality)
P$att6 <- apollo_ol(list(outcomeOrdered=att6,V=z_att6*attmultimodality,
tau=list(tau_att6_1,tau_att6_2,tau_att6_3,tau_att6_4),
rows=(sp_scen==1),componentName="att6"),functionality)
## utility for each alternative ------------------------------------------
V <- list()
V$privatecar <- asc_pc +
b_attc * privatecar.attc +
b_conttc*privatecar.conttc*privatecar.attc +
b_uncerc*privatecar.uncer*privatecar.conttc*privatecar.attc +
b_cost * privatecar.costc +
b_parkfee*privatecar.parkfeec
V$ubercar <- asc_ubercar +
b_attc * ridehailingcar.attc +
b_conttc*ridehailingcar.conttc*ridehailingcar.attc +
b_uncerc*ridehailingcar.uncer*ridehailingcar.conttc*ridehailingcar.attc +
b_cost * ridehailingcar.costu +
b_wait * ridehailingcar.waitu
V$cng <- asc_cng +
b_attc * ridehailingcar.attc +
b_conttc*ridehailingcar.conttc*ridehailingcar.attc +
b_uncerc*ridehailingcar.uncer*ridehailingcar.conttc*ridehailingcar.attc +
b_cost * ridehailingcng.costu +
b_wait * ridehailingcar.waitu
V$bike <- asc_bike +
b_attbike * ridehailingbike.attc +
b_conttbike*ridehailingbike.conttc*ridehailingbike.attc +
b_uncerbike*ridehailingcar.uncer*ridehailingbike.conttc*ridehailingbike.attc +
b_cost * ridehailingbike.costu +
b_wait * ridehailingcar.waitu
V$rickshaw <- asc_rickshaw +
b_attr * rickshaw.attr +
b_conttr*rickshaw.conttc*rickshaw.attr +
b_uncerr*rickshaw.uncer*rickshaw.conttc*rickshaw.attr +
b_cost * rickshaw.costr +
b_wait * rickshaw.waitr +
b_transfers*rickshaw.transfersr
V$bus <- asc_bus +
b_attb * bus.attb +
b_conttb*bus.conttc*bus.attb +
b_uncerb*bus.uncer*bus.conttc*bus.attb +
b_cost * bus.costb +
b_walk * bus.walk +
b_wait * bus.waitr +
b_transfers*bus.transfers +
b_crowd_2*bus.crowd2 + b_crowd_3*bus.crowd3 +
b_schedule*bus.schedule
V$transit <- asc_transit +
b_attt * transit.attt +
b_conttt*transit.conttt*transit.attt +
b_cost * transit.costt +
b_walk * transit.walk +
b_wait * transit.waitu +
b_transfers*transit.transfers +
b_crowd_2*transit.crowd2 + b_crowd_3*transit.crowd3 +
b_schedule*transit.schedule +
b_pnr*transit.pnrt + b_grade*transit.gradet
avail <- list(privatecar=pc_avail, ubercar=rhcar_avail, cng=rhcng_avail,
bike=rhbike_avail, rickshaw=rick_avail,
bus=bus_avail, transit=transit_avail)
mnl_set <- list(alternatives = c(privatecar=1, ubercar=2, cng=3, bike=4,
rickshaw=5, bus=6, transit=7),
avail = avail,
choiceVar = best,
V = V,
componentName= "choice")
P$choice <- apollo_mnl(mnl_set, functionality)
## combine, average draws, panel etc. --------------------------------------
P <- apollo_combineModels(P, apollo_inputs, functionality)
P <- apollo_panelProd (P, apollo_inputs, functionality)
P <- apollo_avgInterDraws(P, apollo_inputs, functionality)
P <- apollo_prepareProb (P, apollo_inputs, functionality)
return(P)
}
# ─────────────────────────────────────────────────────────────────────────────
# 6. Estimation -------------------------------------------------------------
# ─────────────────────────────────────────────────────────────────────────────
estimate_settings <- list(maxIterations = 1500, estimationRoutine = "BFGS")
modechoice_model <- apollo_estimate(
apollo_beta,
apollo_fixed,
apollo_probabilities,
apollo_inputs,
estimate_settings
)
apollo_modelOutput(modechoice_model)
##############output
Preparing user-defined functions.
WARNING: The pre-processing of 'apollo_probabilities' failed in initial testing. Your model may still run, but this indicates a potential problem. Please contact the
developers for assistance!
Testing likelihood function...
INFORMATION: No coding provided for Ordered model component "do4", so assuming outcomeOrdered goes from 1 to 5
Overview of choices for OL model component do4:
1 2 3 4 5
Times chosen 13.00 463.00 152.00 357.00 86.00
Percentage chosen overall 1.21 43.23 14.19 33.33 8.03
INFORMATION: No coding provided for Ordered model component "do5", so assuming outcomeOrdered goes from 1 to 5
Overview of choices for OL model component do5:
1 2 3 4 5
Times chosen 26.00 365.00 182.00 391.00 107.00
Percentage chosen overall 2.43 34.08 16.99 36.51 9.99
INFORMATION: No coding provided for Ordered model component "hs1", so assuming outcomeOrdered goes from 1 to 5
Overview of choices for OL model component hs1:
1 2 3 4 5
Times chosen 3.00 148.00 213.00 598.00 109.00
Percentage chosen overall 0.28 13.82 19.89 55.84 10.18
INFORMATION: No coding provided for Ordered model component "hs2", so assuming outcomeOrdered goes from 1 to 5
Overview of choices for OL model component hs2:
1 2 3 4 5
Times chosen 7.00 219.00 218.00 451.00 176.00
Percentage chosen overall 0.65 20.45 20.35 42.11 16.43
INFORMATION: No coding provided for Ordered model component "hs3", so assuming outcomeOrdered goes from 1 to 5
Overview of choices for OL model component hs3:
1 2 3 4 5
Times chosen 19.00 253.00 81.00 570.00 148.00
Percentage chosen overall 1.77 23.62 7.56 53.22 13.82
INFORMATION: No coding provided for Ordered model component "hs4", so assuming outcomeOrdered goes from 1 to 5
Overview of choices for OL model component hs4:
1 2 3 4 5
Times chosen 49.00 366.00 85.00 480.00 91.0
Percentage chosen overall 4.58 34.17 7.94 44.82 8.5
INFORMATION: No coding provided for Ordered model component "hs5", so assuming outcomeOrdered goes from 1 to 5
Overview of choices for OL model component hs5:
1 2 3 4 5
Times chosen 18.00 425.00 141.00 397.00 90.0
Percentage chosen overall 1.68 39.68 13.17 37.07 8.4
INFORMATION: No coding provided for Ordered model component "hs6", so assuming outcomeOrdered goes from 1 to 5
Overview of choices for OL model component hs6:
1 2 3 4 5
Times chosen 18.00 410.00 152.00 384.00 107.00
Percentage chosen overall 1.68 38.28 14.19 35.85 9.99
INFORMATION: No coding provided for Ordered model component "hs7", so assuming outcomeOrdered goes from 1 to 5
Overview of choices for OL model component hs7:
1 2 3 4 5
Times chosen 6.00 278.00 190.00 489.00 108.00
Percentage chosen overall 0.56 25.96 17.74 45.66 10.08
INFORMATION: No coding provided for Ordered model component "ka1", so assuming outcomeOrdered goes from 1 to 5
Overview of choices for OL model component ka1:
1 2 3 4 5
Times chosen 1.00 57.00 65.00 687.00 261.00
Percentage chosen overall 0.09 5.32 6.07 64.15 24.37
INFORMATION: No coding provided for Ordered model component "ka2", so assuming outcomeOrdered goes from 1 to 5
Overview of choices for OL model component ka2:
1 2 3 4 5
Times chosen 3.00 114.00 134.00 533.00 287.0
Percentage chosen overall 0.28 10.64 12.51 49.77 26.8
INFORMATION: No coding provided for Ordered model component "ka3", so assuming outcomeOrdered goes from 1 to 5
Overview of choices for OL model component ka3:
1 2 3 4 5
Times chosen 2.00 84.00 124.00 624.00 237.00
Percentage chosen overall 0.19 7.84 11.58 58.26 22.13
INFORMATION: No coding provided for Ordered model component "sn1", so assuming outcomeOrdered goes from 1 to 5
Overview of choices for OL model component sn1:
1 2 3 4 5
Times chosen 7.00 310.00 270.00 409.00 75
Percentage chosen overall 0.65 28.94 25.21 38.19 7
INFORMATION: No coding provided for Ordered model component "sn2", so assuming outcomeOrdered goes from 1 to 5
Overview of choices for OL model component sn2:
1 2 3 4 5
Times chosen 8.00 310.00 282.00 369.00 102.00
Percentage chosen overall 0.75 28.94 26.33 34.45 9.52
INFORMATION: No coding provided for Ordered model component "sn3", so assuming outcomeOrdered goes from 1 to 5
Overview of choices for OL model component sn3:
1 2 3 4 5
Times chosen 26.00 313.00 284.00 385.00 63.00
Percentage chosen overall 2.43 29.23 26.52 35.95 5.88
INFORMATION: No coding provided for Ordered model component "att1", so assuming outcomeOrdered goes from 1 to 5
Overview of choices for OL model component att1:
1 2 3 4 5
Times chosen 12.00 206.00 210.00 597.00 46.0
Percentage chosen overall 1.12 19.23 19.61 55.74 4.3
INFORMATION: No coding provided for Ordered model component "att2", so assuming outcomeOrdered goes from 1 to 5
Overview of choices for OL model component att2:
1 2 3 4 5
Times chosen 13.00 151.0 201.00 562.00 144.00
Percentage chosen overall 1.21 14.1 18.77 52.47 13.45
INFORMATION: No coding provided for Ordered model component "att3", so assuming outcomeOrdered goes from 1 to 5
Overview of choices for OL model component att3:
1 2 3 4 5
Times chosen 10.00 152.00 242.0 593.00 74.00
Percentage chosen overall 0.93 14.19 22.6 55.37 6.91
INFORMATION: No coding provided for Ordered model component "att5", so assuming outcomeOrdered goes from 1 to 5
Overview of choices for OL model component att5:
1 2 3 4 5
Times chosen 7.00 134.00 215.00 615.00 100.00
Percentage chosen overall 0.65 12.51 20.07 57.42 9.34
INFORMATION: No coding provided for Ordered model component "att6", so assuming outcomeOrdered goes from 1 to 5
Overview of choices for OL model component att6:
1 2 3 4 5
Times chosen 7.00 121.0 235.00 627.00 81.00
Percentage chosen overall 0.65 11.3 21.94 58.54 7.56
Overview of choices for MNL model component choice:
privatecar ubercar cng bike rickshaw bus transit
Times available 149.00 120.0 290.00 890.00 538.00 1225.00 1516.00
Times chosen 117.00 15.0 61.00 369.00 97.00 293.00 1190.00
Percentage chosen overall 5.46 0.7 2.85 17.23 4.53 13.68 55.56
Percentage chosen when available 78.52 12.5 21.03 41.46 18.03 23.92 78.50
Log-likelihood calculation fails at starting values!
Affected individuals:
ID LL
51 -Inf
52 -Inf
56 NaN
57 NaN
67 -Inf
68 -Inf
71 NaN
74 -Inf
77 NaN
120 NaN
126 -Inf
127 -Inf
128 NaN
130 -Inf
132 -Inf
133 NaN
135 -Inf
139 NaN
142 NaN
144 -Inf
145 -Inf
147 NaN
148 -Inf
149 -Inf
151 NaN
152 NaN
153 -Inf
154 NaN
156 -Inf
159 NaN
160 -Inf
161 -Inf
162 -Inf
163 -Inf
165 NaN
172 -Inf
173 NaN
175 -Inf
186 -Inf
189 NaN
204 -Inf
205 -Inf
206 -Inf
208 NaN
210 -Inf
211 NaN
212 -Inf
213 NaN
214 -Inf
215 NaN
216 NaN
220 NaN
224 -Inf
227 -Inf
228 -Inf
232 -Inf
233 -Inf
234 -Inf
238 NaN
240 NaN
244 -Inf
249 -Inf
253 NaN
256 -Inf
257 NaN
258 NaN
259 -Inf
260 NaN
264 NaN
265 NaN
274 NaN
275 -Inf
276 -Inf
277 -Inf
278 NaN
279 -Inf
280 -Inf
281 -Inf
282 NaN
283 -Inf
287 -Inf
294 -Inf
295 NaN
296 -Inf
297 -Inf
298 -Inf
303 -Inf
304 -Inf
307 -Inf
309 -Inf
313 -Inf
314 -Inf
321 NaN
322 -Inf
324 -Inf
326 NaN
331 NaN
332 -Inf
333 -Inf
337 -Inf
344 NaN
348 -Inf
349 -Inf
350 -Inf
351 NaN
352 NaN
354 NaN
356 -Inf
358 -Inf
359 -Inf
360 -Inf
361 -Inf
363 NaN
364 -Inf
365 -Inf
366 -Inf
367 NaN
368 -Inf
370 NaN
372 -Inf
373 NaN
374 NaN
376 NaN
379 NaN
380 NaN
382 -Inf
383 -Inf
385 -Inf
388 -Inf
389 -Inf
393 -Inf
394 NaN
395 -Inf
397 -Inf
399 NaN
401 -Inf
405 -Inf
414 -Inf
416 -Inf
419 -Inf
421 -Inf
423 -Inf
424 -Inf
425 -Inf
426 -Inf
428 -Inf
430 NaN
431 -Inf
432 -Inf
434 -Inf
435 -Inf
436 NaN
437 -Inf
438 -Inf
439 -Inf
440 NaN
443 -Inf
446 -Inf
451 -Inf
452 -Inf
453 -Inf
454 NaN
455 -Inf
456 -Inf
458 -Inf
459 -Inf
461 NaN
464 NaN
465 NaN
466 NaN
472 -Inf
474 -Inf
477 NaN
478 -Inf
479 -Inf
481 -Inf
482 -Inf
488 NaN
489 -Inf
494 NaN
497 -Inf
498 -Inf
499 -Inf
500 -Inf
502 -Inf
506 -Inf
507 -Inf
512 -Inf
513 -Inf
515 NaN
518 NaN
519 NaN
521 -Inf
525 -Inf
526 NaN
527 -Inf
528 NaN
531 -Inf
532 NaN
533 -Inf
534 NaN
535 -Inf
537 -Inf
538 NaN
540 -Inf
541 -Inf
542 -Inf
544 NaN
545 NaN
547 NaN
548 -Inf
553 -Inf
554 NaN
556 -Inf
557 NaN
560 -Inf
561 -Inf
564 -Inf
568 -Inf
572 -Inf
573 NaN
574 -Inf
576 -Inf
577 NaN
578 -Inf
580 -Inf
582 -Inf
585 -Inf
589 -Inf
590 NaN
591 -Inf
592 -Inf
593 -Inf
595 -Inf
596 NaN
597 -Inf
600 -Inf
602 NaN
605 -Inf
606 NaN
607 NaN
609 NaN
610 NaN
612 NaN
613 -Inf
614 NaN
615 NaN
616 -Inf
619 NaN
622 NaN
625 -Inf
631 NaN
635 -Inf
637 -Inf
638 -Inf
639 NaN
640 -Inf
645 -Inf
646 NaN
647 -Inf
648 -Inf
649 -Inf
650 -Inf
651 -Inf
654 -Inf
655 -Inf
657 -Inf
658 NaN
659 NaN
660 -Inf
662 -Inf
663 NaN
664 -Inf
665 NaN
666 -Inf
667 -Inf
668 -Inf
669 NaN
671 NaN
673 NaN
675 -Inf
676 -Inf
677 -Inf
679 -Inf
681 -Inf
682 -Inf
688 NaN
693 NaN
695 -Inf
697 -Inf
698 -Inf
700 -Inf
701 -Inf
702 -Inf
704 NaN
705 NaN
708 -Inf
709 -Inf
710 -Inf
715 -Inf
716 NaN
718 -Inf
721 -Inf
722 -Inf
723 -Inf
727 NaN
728 -Inf
730 NaN
731 -Inf
732 -Inf
734 -Inf
735 -Inf
736 -Inf
737 -Inf
739 -Inf
741 -Inf
742 -Inf
743 NaN
746 -Inf
748 NaN
750 NaN
752 NaN
753 NaN
754 -Inf
756 NaN
758 -Inf
759 -Inf
760 NaN
761 -Inf
762 -Inf
764 NaN
765 -Inf
766 NaN
769 -Inf
771 -Inf
772 -Inf
773 -Inf
774 -Inf
775 -Inf
776 -Inf
777 -Inf
778 NaN
783 -Inf
784 -Inf
785 -Inf
786 -Inf
789 NaN
792 NaN
794 -Inf
795 -Inf
796 NaN
797 -Inf
800 NaN
801 -Inf
802 NaN
803 -Inf
805 NaN
806 NaN
807 NaN
808 -Inf
811 NaN
812 -Inf
813 NaN
815 NaN
817 NaN
818 NaN
819 NaN
820 -Inf
821 -Inf
824 NaN
827 NaN
832 -Inf
836 NaN
843 -Inf
850 NaN
853 -Inf
854 NaN
855 -Inf
856 -Inf
858 -Inf
861 -Inf
862 NaN
869 NaN
870 NaN
876 -Inf
877 -Inf
878 -Inf
881 -Inf
882 NaN
883 -Inf
884 NaN
886 NaN
887 -Inf
888 -Inf
890 -Inf
891 NaN
893 -Inf
895 -Inf
897 -Inf
899 NaN
900 -Inf
901 NaN
902 NaN
903 NaN
904 -Inf
906 NaN
908 NaN
909 -Inf
910 -Inf
911 -Inf
912 NaN
914 -Inf
921 NaN
922 -Inf
923 -Inf
924 NaN
926 -Inf
927 -Inf
928 -Inf
929 -Inf
930 -Inf
932 -Inf
933 -Inf
935 NaN
936 NaN
940 -Inf
942 NaN
944 -Inf
946 NaN
948 -Inf
952 NaN
954 NaN
957 -Inf
959 NaN
960 -Inf
962 NaN
963 -Inf
964 -Inf
965 NaN
967 -Inf
972 NaN
974 NaN
975 NaN
979 NaN
981 NaN
984 -Inf
986 -Inf
990 NaN
991 -Inf
993 NaN
994 -Inf
996 -Inf
999 NaN
1000 -Inf
1002 NaN
1003 -Inf
1005 -Inf
1007 -Inf
1008 -Inf
1009 NaN
1010 NaN
1013 -Inf
1014 -Inf
1015 -Inf
1016 -Inf
1020 -Inf
1021 NaN
1022 NaN
1025 -Inf
1029 -Inf
1030 NaN
1031 NaN
1033 -Inf
1034 -Inf
1035 -Inf
1036 -Inf
1038 -Inf
1040 -Inf
1043 -Inf
1048 -Inf
1051 -Inf
1052 -Inf
1054 -Inf
1055 NaN
1056 -Inf
1060 NaN
1061 NaN
1063 -Inf
1065 -Inf
1066 -Inf
1068 NaN
1070 NaN
1071 -Inf
1072 -Inf
1073 -Inf
1075 -Inf
1077 NaN
1081 -Inf
1083 -Inf
1084 NaN
[ reached 'max' / getOption("max.print") -- omitted 257 rows ]
Error in apollo_estimate(apollo_beta, apollo_fixed, apollo_probabilities, :
CALCULATION ISSUE - Log-likelihood calculation fails at values close to the starting values!

Add Comment

Please, Sign In to add comment