Error when weight column is added in an error-component logit model
Posted: 01 Mar 2023, 11:08
Dear Apollo Team,
I have a problem with adding weight to my estimation. I am estimating a mode choice model of error-components logit type in a panel data set. Without weights, I have no problems and estimation results are produced. When I want the model to consider weights I will encounter this error:
The weights assigned to some observations are really small and I thought this may have caused the issue. But inflating the weights did not solve the issue. For your information, my code is written below.
Best regards,
Mehdi
I have a problem with adding weight to my estimation. I am estimating a mode choice model of error-components logit type in a panel data set. Without weights, I have no problems and estimation results are produced. When I want the model to consider weights I will encounter this error:
Code: Select all
Testing influence of parameters
During testing, Apollo added disturbances smaller than 0.001 to all starting values.
This led to a log-likelihood calculation failure!
Affected individuals:
[color=#BF0000]Error in apollo_estimate(apollo_beta, apollo_fixed, apollo_probabilities, :
Log-likelihood calculation fails at values close to the starting values![/color]
Best regards,
Mehdi
Code: Select all
### Clear memory
rm(list = ls())
### Load relevant libraries
library(apollo)
library(tidyverse)
### Initialize code
apollo_initialise()
# Write the model description which will also be the folder name of outputs
modelDescription <- "ECL1_WEIGHTED"
# Address
address <- paste("C:/Users/rekendat2/Documents/Hanif/Models/",
modelDescription,
sep="")
### Set core controls
# Some other useful variables: weights, workInLogs
apollo_control <- list(
modelName = modelDescription,
modelDescr = modelDescription,
indivID = "tracker_id",
outputDirectory = address,
mixing = TRUE,
panelData = TRUE,
nCores = 11,
weights = "adjWeight"
)
### Load the data
# Upload the database which does not have weight column
database <- read.csv(
"C:/Users/rekendat2/Documents/Hanif/input_work_panel.csv",
header = TRUE,
sep = ","
)
# Upload the weights file: each user is laid to a weight multiplier
weightsFile <- readxl::read_excel(
"C:/Users/rekendat2/Documents/Hanif/weight_per_tracker_id.xlsx" )
database <- database %>%
left_join(weightsFile, by="tracker_id") %>%
mutate(adjWeight = weight * (162232 / sum(weight)))
### Vector of parameters, including any that are kept fixed in estimation
apollo_beta <- c(ASC_b = 0,
ASC_w = 0,
ASC_c = 0,
ASC_pt = 0,
ASC_ps = 0,
MED_DIST_b = 0,
MED_DIST_w = 0,
MED_DIST_c = 0,
MED_DIST_pt = 0,
MED_DIST_ps = 0,
LNG_DIST_b = 0,
LNG_DIST_w = 0,
LNG_DIST_c = 0,
LNG_DIST_pt = 0,
LNG_DIST_ps = 0,
RAIN_b = 0,
RAIN_w = 0,
RAIN_c = 0,
RAIN_pt = 0,
RAIN_ps = 0,
MALE_b = 0,
MALE_w = 0,
MALE_c = 0,
MALE_pt = 0,
MALE_ps = 0,
AGE30to44_b = 0,
AGE30to44_w = 0,
AGE30to44_c = 0,
AGE30to44_pt = 0,
AGE30to44_ps = 0,
AGE45to64_b = 0,
AGE45to64_w = 0,
AGE45to64_c = 0,
AGE45to64_pt = 0,
AGE45to64_ps = 0,
AGE65_b = 0,
AGE65_w = 0,
AGE65_c = 0,
AGE65_pt = 0,
AGE65_ps = 0,
LARGE_HHLD_b = 0,
LARGE_HHLD_w = 0,
LARGE_HHLD_c = 0,
LARGE_HHLD_pt = 0,
LARGE_HHLD_ps= 0,
WITH_CHLD_b = 0,
WITH_CHLD_w = 0,
WITH_CHLD_c = 0,
WITH_CHLD_pt = 0,
WITH_CHLD_ps = 0,
WITHOUT_CHLD_b = 0,
WITHOUT_CHLD_w = 0,
WITHOUT_CHLD_c = 0,
WITHOUT_CHLD_pt = 0,
WITHOUT_CHLD_ps = 0,
MED_EDU_b = 0,
MED_EDU_w = 0,
MED_EDU_c = 0,
MED_EDU_pt = 0,
MED_EDU_ps = 0,
HIGH_EDU_b = 0,
HIGH_EDU_w = 0,
HIGH_EDU_c = 0,
HIGH_EDU_pt = 0,
HIGH_EDU_ps = 0,
MED_DNST_b = 0,
MED_DNST_w = 0,
MED_DNST_c = 0,
MED_DNST_pt = 0,
MED_DNST_ps = 0,
HI_DNST_b = 0,
HI_DNST_w = 0,
HI_DNST_c = 0,
HI_DNST_pt = 0,
HI_DNST_ps = 0,
sigma_b = 1,
sigma_w = 1,
sigma_c = 1,
sigma_pt = 1,
sigma_ps = 1
)
### Vector with names (in quotes) of parameters to be kept fixed at
### their starting value in
apollo_fixed = c("ASC_b",
"MED_DIST_b",
"LNG_DIST_b",
"RAIN_b",
"AGE30to44_b",
"AGE45to64_b",
"AGE65_b",
"MED_EDU_b",
"HIGH_EDU_b",
"MALE_b",
"LARGE_HHLD_b",
"WITH_CHLD_b",
"WITHOUT_CHLD_b",
"MED_DNST_b",
"HI_DNST_b"
)
### Set parameters for generating draws
apollo_draws = list(
interDrawsType = "mlhs",
interNDraws = 500,
interNormDraws = c("draws_b",
"draws_w",
"draws_c",
"draws_ps",
"draws_pt")
)
### Create random parameters
apollo_randCoeff = function(apollo_beta, apollo_inputs){
randcoeff = list()
randcoeff[["ec_b"]] = draws_b * sigma_b
randcoeff[["ec_w"]] = draws_w * sigma_w
randcoeff[["ec_c"]] = draws_c * sigma_c
randcoeff[["ec_pt"]] = draws_pt * sigma_pt
randcoeff[["ec_ps"]] = draws_ps * sigma_ps
return(randcoeff)
}
apollo_inputs=apollo_validateInputs()
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()
### Create alternative specific constants and coefficients using interactions
### with socio-demographics
### List of utilities: these must use the same names as in mnl_settings,
### order is irrelevant
V = list()
V[["b"]] = ASC_b + MED_DIST_b * MED_DIST + LNG_DIST_b * LNG_DIST + RAIN_b * RAIN + MALE_b * MALE + AGE30to44_b * AGE30to44 + AGE45to64_b * AGE45to64 + AGE65_b * AGE65 + LARGE_HHLD_b * LARGE_HHLD + MED_EDU_b * MED_EDU + HIGH_EDU_b * HIGH_EDU + WITH_CHLD_b * WITH_CHLD + WITHOUT_CHLD_b * WITHOUT_CHLD + MED_DNST_b * MED_DNST + HI_DNST_b * HI_DNST + ec_b
V[["w"]] = ASC_w + MED_DIST_w * MED_DIST + LNG_DIST_w * LNG_DIST + RAIN_w * RAIN + MALE_w * MALE + AGE30to44_w * AGE30to44 + AGE45to64_w * AGE45to64 + AGE65_w * AGE65 + LARGE_HHLD_w * LARGE_HHLD + MED_EDU_w * MED_EDU + HIGH_EDU_w * HIGH_EDU + WITH_CHLD_w * WITH_CHLD + WITHOUT_CHLD_w * WITHOUT_CHLD + MED_DNST_w * MED_DNST + HI_DNST_w * HI_DNST + ec_w
V[["c"]] = ASC_c + MED_DIST_c * MED_DIST + LNG_DIST_c * LNG_DIST + RAIN_c * RAIN + MALE_c * MALE + AGE30to44_c * AGE30to44 + AGE45to64_c * AGE45to64 + AGE65_c * AGE65 + LARGE_HHLD_c * LARGE_HHLD + MED_EDU_c * MED_EDU + HIGH_EDU_c * HIGH_EDU + WITH_CHLD_c * WITH_CHLD + WITHOUT_CHLD_c * WITHOUT_CHLD + MED_DNST_c * MED_DNST + HI_DNST_c * HI_DNST + ec_c
V[["pt"]] = ASC_pt + MED_DIST_pt * MED_DIST + LNG_DIST_pt * LNG_DIST + RAIN_pt * RAIN + MALE_pt * MALE + AGE30to44_pt * AGE30to44 + AGE45to64_pt * AGE45to64 + AGE65_pt * AGE65 + LARGE_HHLD_pt * LARGE_HHLD + MED_EDU_pt * MED_EDU + HIGH_EDU_pt * HIGH_EDU + WITH_CHLD_pt * WITH_CHLD + WITHOUT_CHLD_pt * WITHOUT_CHLD + MED_DNST_pt * MED_DNST + HI_DNST_pt * HI_DNST + ec_pt
V[["ps"]] = ASC_ps + MED_DIST_ps * MED_DIST + LNG_DIST_ps * LNG_DIST + RAIN_ps * RAIN + MALE_ps * MALE + AGE30to44_ps * AGE30to44 + AGE45to64_ps * AGE45to64 + AGE65_ps * AGE65 + LARGE_HHLD_ps * LARGE_HHLD + MED_EDU_ps * MED_EDU + HIGH_EDU_ps * HIGH_EDU + WITH_CHLD_ps * WITH_CHLD + WITHOUT_CHLD_ps * WITHOUT_CHLD + MED_DNST_ps * MED_DNST + HI_DNST_ps * HI_DNST + ec_ps
### Define Settings for MNL model component
mnl_settings = list(
alternatives = c(b=1, w=2, c=3, pt=4, ps=5),
avail = list(b=av_b, w=av_w, c=av_c, pt=av_pt, ps=av_ps),
choiceVar = choice,
utilities = V
)
### Compute probabilities using MNL model
P[["model"]] = apollo_mnl(mnl_settings,
functionality)
### Take product across observation for same individual
P = apollo_panelProd(P,
apollo_inputs,
functionality)
### Average across inter-individual draws (what is it??)
P = apollo_avgInterDraws(P,
apollo_inputs,
functionality)
### This part is added due to the introduction of weights into estimation
P = apollo_weighting(P,
apollo_inputs,
functionality)
### Prepare and return outputs of function
P = apollo_prepareProb(P,
apollo_inputs,
functionality)
return(P)
}
### Settings for the estimation
# other useful settings might be: estimationRoutine, hessianRoutine
estimate_settings = list(
maxIterations = 400
)
# Estimation
model = apollo_estimate(apollo_beta,
apollo_fixed,
apollo_probabilities,
apollo_inputs,
estimate_settings
)