I have encountered the same error that
Testing likelihood function...
INFORMATION: Setting "avail" is missing, so full availability is assumed.
Error in apollo_validate(el_settings, modelType, functionality, apollo_inputs) :
INPUT ISSUE - Only one alternative is available for each observation for model component "model!
I am using read.csv and trying to build the exploded logit model. However, there was no problem when I built the MNL model.
And this is my code:
Code: Select all
# ################################################################# #
#### LOAD LIBRARY AND DEFINE CORE SETTINGS ####
# ################################################################# #
### Clear memory
rm(list = ls())
### Load Apollo library
library(apollo)
### Initialise code
apollo_initialise()
### Set core controls
apollo_control = list(
modelName = "EL_Strategy",
modelDescr = "Exploded logit model on all data of strategy choice for car owners",
indivID = "RID",
outputDirectory = "output"
)
# ################################################################# #
#### LOAD DATA AND APPLY ANY TRANSFORMATIONS ####
# ################################################################# #
### Loading data from package
### if data is to be loaded from a file (e.g. called data.csv),
### the code would be: database = read.csv("data.csv",header=TRUE)
database = read.csv("/Users/josephwu/Library/CloudStorage/OneDrive-TheUniversityofQueensland/Brisbane micromobility survey/EMM SP study/Data/all_data/models/Strategy_all/exploded_logit/csv_strategy_with_car_demo.csv",header=TRUE)
### for data dictionary, use ?apollo_modeChoiceData
# ################################################################# #
#### DEFINE MODEL PARAMETERS ####
# ################################################################# #
### Vector of parameters, including any that are kept fixed in estimation
apollo_beta=c(asc_direct = 0,
asc_replace = 0,
asc_optout = 0,
b_type_direct_eb = 0,
b_type_direct_es = 0,
b_type_replace_eb = 0,
b_type_replace_es = 0,
b_fp_direct_1 = 0,
b_fp_direct_2 = 0,
b_fp_direct_3 = 0,
b_fp_direct_4 = 0,
b_fp_direct_5 = 0,
b_fp_replace_1 = 0,
b_fp_replace_2 = 0,
b_fp_replace_3 = 0,
b_fp_replace_4 = 0,
b_fp_replace_5 = 0,
b_rate_direct_1 = 0,
b_rate_direct_2 = 0,
b_rate_direct_3 = 0,
b_rate_replace_1 = 0,
b_rate_replace_2 = 0,
b_rate_replace_3 = 0,
b_rr_direct_1 = 0,
b_rr_direct_2 = 0,
b_rr_direct_3 = 0,
b_rr_replace_1 = 0,
b_rr_replace_2 = 0,
b_rr_replace_3 = 0,
b_am_yes_direct = 0,
b_am_no_direct = 0,
b_am_yes_replace = 0,
b_am_no_replace = 0,
scale_1 = 1,
scale_2 = 1,
scale_3 = 1)
### Vector with names (in quotes) of parameters to be kept fixed at their starting value in apollo_beta, use apollo_beta_fixed = c() if none
apollo_fixed = c("asc_optout","b_type_direct_es","b_type_replace_es","b_fp_direct_1","b_rate_direct_1","b_fp_replace_1",
"b_rate_replace_1","b_am_no_direct","b_am_no_replace","b_rr_direct_1","b_rr_replace_1","scale_1")
# ################################################################# #
#### GROUP AND VALIDATE INPUTS ####
# ################################################################# #
apollo_inputs = apollo_validateInputs()
# ################################################################# #
#### DEFINE MODEL AND LIKELIHOOD FUNCTION ####
# ################################################################# #
apollo_probabilities=function(apollo_beta, apollo_inputs, functionality="estimate"){
### Attach inputs and detach after function exit
apollo_attach(apollo_beta, apollo_inputs)
on.exit(apollo_detach(apollo_beta, apollo_inputs))
### Create list of probabilities P
P = list()
### List of utilities: these must use the same names as in mnl_settings, order is irrelevant
V = list()
# V[["direct"]] = asc_direct + b_type_direct_eb * ( a1_x1 == 1 ) + b_type_direct_es * ( a1_x1 == 2 ) + b_fp_direct_1 * (a1_x2 == 1 ) + b_fp_direct_1 * (a1_x2 == 1 ) +
# b_fp_direct_2 * (a1_x2 == 2 ) + b_fp_direct_3 * (a1_x2 == 3 ) + b_fp_direct_4 * (a1_x2 == 4 ) + b_fp_direct_5 * (a1_x2 == 5 ) +
# b_rate_direct_1 * ( a1_x3 == 1) + b_rate_direct_2 * ( a1_x3 == 2) +
# b_rate_direct_3 * ( a1_x3 == 3) + b_rr_direct * a1_x4_value + b_am_yes_direct * ( a1_x5 == 1) + b_am_no_direct * ( a1_x5 == 2)
V[["direct"]] = asc_direct + b_type_direct_eb * ( a1_x1 == 1 ) + b_type_direct_es * ( a1_x1 == 2 ) + b_fp_direct_1 * (a1_x2 == 1 ) +
b_fp_direct_2 * (a1_x2 == 2 ) + b_fp_direct_3 * (a1_x2 == 3 ) + b_fp_direct_4 * (a1_x2 == 4 ) + b_fp_direct_5 * (a1_x2 == 5 ) +
b_rate_direct_1 * ( a1_x3 == 1) + b_rate_direct_2 * ( a1_x3 == 2) +
b_rate_direct_3 * ( a1_x3 == 3) + b_rr_direct_1 * ( a1_x4 == 1 ) + b_rr_direct_2 * ( a1_x4 == 2 ) + b_rr_direct_3 * ( a1_x4 == 3 ) + b_am_yes_direct * ( a1_x5 == 1) + b_am_no_direct * ( a1_x5 == 2)
# V[["replace"]] = asc_replace + b_type_replace_eb * ( a1_x1 == 1 ) + b_type_replace_es * ( a1_x1 == 2 ) + b_fp_replace_1 * (a1_x2 == 1 ) + b_fp_replace_1 * (a1_x2 == 1 ) +
# b_fp_replace_2 * (a1_x2 == 2 ) + b_fp_replace_3 * (a1_x2 == 3 ) + b_fp_replace_4 * (a1_x2 == 4 ) + b_fp_replace_5 * (a1_x2 == 5 ) + b_rate_replace_1 * ( a2_x3 == 1) +
# b_rate_replace_2 * ( a2_x3 == 2) +
# b_rate_replace_3 * ( a2_x3 == 3) + b_rr_replace * a2_x4_value + b_am_yes_replace * ( a2_x5 == 1) + b_am_no_replace * ( a2_x5 == 2)
V[["replace"]] = asc_replace + b_type_replace_eb * ( a1_x1 == 1 ) + b_type_replace_es * ( a1_x1 == 2 ) + b_fp_replace_1 * (a1_x2 == 1 ) +
b_fp_replace_2 * (a1_x2 == 2 ) + b_fp_replace_3 * (a1_x2 == 3 ) + b_fp_replace_4 * (a1_x2 == 4 ) + b_fp_replace_5 * (a1_x2 == 5 ) + b_rate_replace_1 * ( a2_x3 == 1) +
b_rate_replace_2 * ( a2_x3 == 2) +
b_rate_replace_3 * ( a2_x3 == 3) + b_rr_replace_1 * ( a2_x4 == 1 ) + b_rr_replace_2 * ( a2_x4 == 2 )+ b_rr_replace_3 * ( a2_x4 == 3 ) + b_am_yes_replace * ( a2_x5 == 1) + b_am_no_replace * ( a2_x5 == 2)
V[["optout"]] = asc_optout
### Define settings for MNL model component
el_settings = list(
alternatives = c(direct=1, replace=2, optout=3),
#avail = list(direct=1, replace=1, optout=1),
choiceVars = list(pref1, pref3, third_pref),
utilities = V,
scales = list(scale_1,scale_2,scale_3)
)
### Compute exploded logit probabilities
P[["model"]]=apollo_el(el_settings, functionality)
### Take product across observation for same individual
P = apollo_panelProd(P, apollo_inputs, functionality)
### Prepare and return outputs of function
P = apollo_prepareProb(P, apollo_inputs, functionality)
return(P)
}
# ################################################################# #
#### MODEL ESTIMATION ####
# ################################################################# #
model = apollo_estimate(apollo_beta, apollo_fixed, apollo_probabilities, apollo_inputs)
# ################################################################# #
#### MODEL OUTPUTS ####
# ################################################################# #
# ----------------------------------------------------------------- #
#---- FORMATTED OUTPUT (TO SCREEN) ----
# ----------------------------------------------------------------- #
apollo_modelOutput(model)
# ----------------------------------------------------------------- #
#---- FORMATTED OUTPUT (TO FILE, using model name) ----
# ----------------------------------------------------------------- #
apollo_saveOutput(model)
Best,
Yikang