Individual weights error with LC model
Posted: 20 Nov 2025, 16:01
Hi,
I am running a basic LC model without any covariates, just to build up towards more complex classes. I am using individual weights in my estimation. I know for sure that the weights are correctly specified since I have already estimated RPL models using those weights without issues. However, when I turn to the LC estimation, I encounter the following error:
After running that code I get the following output
I have estimated the model without any weights and it works, so I know the only issue is with the weighting part. I am guessing I am not placing the weighting in the right part of the code, I followed what I was doing and worked for the RPL here.
I would really appreciate any help.
I am running a basic LC model without any covariates, just to build up towards more complex classes. I am using individual weights in my estimation. I know for sure that the weights are correctly specified since I have already estimated RPL models using those weights without issues. However, when I turn to the LC estimation, I encounter the following error:
Below my full code:Error en apollo_weighting(P, apollo_inputs, functionality):INTERNAL ISSUE - When applying weights at the individual level, weights should be the same for all observations of each individual
Code: Select all
apollo_initialise()
# core controls
apollo_control = list(
modelDescr = "Latent class with continuous random parameters on Swiss route choice data",
indivID = "individual_id",
nCores = 4,
outputDirectory = "RESULTS/LC",
weights = "weights" # These weights are at the individual level
)
# PARAMETERS
apollo_beta = c(
mu_b_optout_a = -1.095,
sigma_b_optout_a = 0.5,
mu_b_optout_b = -1.095,
sigma_b_optout_b = 0.5,
mu_b_grass_low_a = 0.227,
sigma_b_grass_low_a = 0.09,
mu_b_grass_low_b = 0.227,
sigma_b_grass_low_b = 0.09,
mu_b_grass_high_a = 0.082,
sigma_b_grass_high_a = 0.3,
mu_b_grass_high_b = -0.082,
sigma_b_grass_high_b = 0.3,
mu_b_species_a = -0.037,
sigma_b_species_a = 0.01,
mu_b_species_b = 0.037,
sigma_b_species_b = 0.01,
mu_b_no_seeds_a = -0.867,
sigma_b_no_seeds_a = 0.4,
mu_b_no_seeds_b = -0.867,
sigma_b_no_seeds_b = 0.4,
mu_b_no_fert_seeds_a= 0.879,
sigma_b_no_fert_seeds_a= 0.4,
mu_b_no_fert_seeds_b= -0.879,
sigma_b_no_fert_seeds_b= 0.4,
mu_b_percent_out_a = -0.008,
sigma_b_percent_out_a = 0.002,
mu_b_percent_out_b = 0.008,
sigma_b_percent_out_b = 0.002,
mu_b_payment_a = -4.13,
sigma_b_payment_a = 2,
mu_b_payment_b = -4.13,
sigma_b_payment_b = 2,
delta_a = 0,
delta_b = 0)
### 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("delta_b")
# ################################################################# #
# RANDOM COMPONENTS ####
# ################################################################# #
### Set parameters for generating draws
apollo_draws = list(
interDrawsType="halton",
interNDraws=500,
interUnifDraws=c(),
interNormDraws=c("draws_tt"),
intraDrawsType="mlhs",
intraNDraws=0,
intraUnifDraws=c(),
intraNormDraws=c()
)
### Create random parameters
apollo_randCoeff = function(apollo_beta, apollo_inputs){
randcoeff = list()
randcoeff[["tt_a"]] = -exp(log_tt_a_mu + log_tt_a_sig*draws_tt)
randcoeff[["tt_b"]] = -exp(log_tt_b_mu + log_tt_b_sig*draws_tt)
return(randcoeff)
}
### Set parameters for generating draws
apollo_draws = list(
interDrawsType = "halton",
interNDraws = 100,
interNormDraws = c("draws_payment","draws_optout","draws_g_low","draws_g_high","draws_species","draws_seeds","draws_seeds_fert","draws_percentout","draws_ascB")
)
### Create random parameters
# only downpay and fbound are negative log-normal, the rest are positive
apollo_randCoeff <- function(apollo_beta, apollo_inputs){
randcoeff <- list()
randcoeff[["b_optout_a"]] = mu_b_optout_a + sigma_b_optout_a * draws_optout
randcoeff[["b_grass_low_a"]] = mu_b_grass_low_a + sigma_b_grass_low_a * draws_g_low
randcoeff[["b_grass_high_a"]] = mu_b_grass_high_a + sigma_b_grass_high_a * draws_g_high
randcoeff[["b_species_a"]] = mu_b_species_a + sigma_b_species_a * draws_species
randcoeff[["b_no_seeds_a"]] = mu_b_no_seeds_a + sigma_b_no_seeds_a* draws_seeds
randcoeff[["b_no_fert_seeds_a"]] = mu_b_no_fert_seeds_a + sigma_b_no_fert_seeds_a * draws_seeds_fert
randcoeff[["b_percent_out_a"]] = mu_b_percent_out_a + sigma_b_percent_out_a * draws_percentout
randcoeff[["b_payment_a"]] = exp(mu_b_payment_a + sigma_b_payment_a * draws_payment) # positive log-normal,
randcoeff[["b_optout_b"]] = mu_b_optout_b + sigma_b_optout_b * draws_optout
randcoeff[["b_grass_low_b"]] = mu_b_grass_low_b + sigma_b_grass_low_b * draws_g_low
randcoeff[["b_grass_high_b"]] = mu_b_grass_high_b + sigma_b_grass_high_b * draws_g_high
randcoeff[["b_species_b"]] = mu_b_species_b + sigma_b_species_b * draws_species
randcoeff[["b_no_seeds_b"]] = mu_b_no_seeds_b + sigma_b_no_seeds_b * draws_seeds
randcoeff[["b_no_fert_seeds_b"]] = mu_b_no_fert_seeds_b + sigma_b_no_fert_seeds_b * draws_seeds_fert
randcoeff[["b_percent_out_b"]] = mu_b_percent_out_b + sigma_b_percent_out_b * draws_percentout
randcoeff[["b_payment_b"]] = exp(mu_b_payment_b + sigma_b_payment_b * draws_payment) # positive log-normal,
return(randcoeff)
}
# ################################################################# #
#### DEFINE LATENT CLASS COMPONENTS ####
# ################################################################# #
apollo_lcPars = function(apollo_beta, apollo_inputs){
lcpars = list()
# Class-specific coefficients
lcpars[["b_optout"]] <- list(b_optout_a, b_optout_b)
lcpars[["b_grass_low"]] <- list(b_grass_low_a, b_grass_low_b)
lcpars[["b_grass_high"]] <- list(b_grass_high_a, b_grass_high_b)
lcpars[["b_species"]] <- list(b_species_a, b_species_b)
lcpars[["b_no_seeds"]] <- list(b_no_seeds_a, b_no_seeds_b)
lcpars[["b_no_fert_seeds"]] <- list(b_no_fert_seeds_a, b_no_fert_seeds_b)
lcpars[["b_percent_out"]] <- list(b_percent_out_a, b_percent_out_b)
lcpars[["b_payment"]] <- list(b_payment_a, b_payment_b)
# Class membership probabilities (no covariates)
#lcpars[["pi_values"]] <- list(1, exp(delta_a + delta_b*0))
V=list()
V[["class_a"]] = delta_a
V[["class_b"]] = delta_b
classAlloc_settings = list(
classes = c(class_a=1, class_b=2),
utilities = V
)
lcpars[["pi_values"]] = apollo_classAlloc(classAlloc_settings)
return(lcpars)
}
# ################################################################# #
#### 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()
### Define settings for MNL model component that are generic across classes
mnl_settings = list(
alternatives = c(alt1 = 1, alt2 = 2, alt3 = 3),
avail = list(alt1 = 1, alt2 = 1, alt3 = 1),
choiceVar = CHOICE
)
### Loop over classes
for(s in 1:2){
### Compute class-specific utilities
### List of utilities: these must use the same names as in mnl_settings, order is irrelevant
V <- list(
alt1 =
b_grass_low[[s]] * grass_low_1 +
b_grass_high[[s]] * grass_high_1 +
b_species[[s]] * Species_1 +
b_no_seeds[[s]] * no_seeds_1 +
b_no_fert_seeds[[s]] * no_fert_seeds_1 +
b_percent_out[[s]] * percent_out_1 +
b_payment[[s]] * payment_1,
alt2 =
b_grass_low[[s]] * grass_low_2 +
b_grass_high[[s]] * grass_high_2 +
b_species[[s]] * Species_2 +
b_no_seeds[[s]] * no_seeds_2 +
b_no_fert_seeds[[s]] * no_fert_seeds_2 +
b_percent_out[[s]] * percent_out_2 +
b_payment[[s]] * payment_2,
alt3 = b_optout[[s]]
)
mnl_settings$utilities = V
### Compute within-class choice probabilities using MNL model
P[[paste0("Class_",s)]] = apollo_mnl(mnl_settings, functionality)
### Apply weights before taking the product of all observations of each indiv
P = apollo_weighting(P, apollo_inputs, functionality)
### Take product across observation for same individual
P[[paste0("Class_",s)]] = apollo_panelProd(P[[paste0("Class_",s)]], apollo_inputs ,functionality)
### Average across inter-individual draws within classes
P[[paste0("Class_",s)]] = apollo_avgInterDraws(P[[paste0("Class_",s)]], apollo_inputs, functionality)
}
### Compute latent class model probabilities
lc_settings = list(inClassProb = P, classProb=pi_values)
P[["model"]] = apollo_lc(lc_settings, apollo_inputs, functionality)
### Prepare and return outputs of function
P = apollo_prepareProb(P, apollo_inputs, functionality)
return(P)
}
# ################################################################# #
#### MODEL ESTIMATION ####
# ################################################################# #
D <- read_dta("DATA/analysis/full_data_estimate.dta") %>% as.data.frame()
D <- subset(D, select = -c(choice_1, choice_2, choice_3))
# Only with the ones that completed all tasks
database <- D %>%
group_by(individual_id) %>%
filter(n_distinct(choice_set) == 6)
apollo_control$modelName <- "LC_RPL_basic_w"
apollo_inputs = apollo_validateInputs()
model = apollo_estimate(apollo_beta, apollo_fixed, apollo_probabilities, apollo_inputs)
apollo_modelOutput(model)
apollo_saveOutput(model)
Code: Select all
> model = apollo_estimate(apollo_beta, apollo_fixed, apollo_probabilities, apollo_inputs)
Preparing user-defined functions.
Testing likelihood function...
Apollo found a model component of type classAlloc without a componentName. The name was set to "classAlloc" by default.
INFORMATION: Setting "avail" is missing, so full availability is assumed.
Apollo found a model component of type MNL without a componentName. The name was set to "Class_1" by default.
Overview of choices for MNL model component Class_1:
alt1 alt2 alt3
Times available 2010.00 2010.0 2010.00
Times chosen 879.00 786.0 345.00
Percentage chosen overall 43.73 39.1 17.16
Percentage chosen when available 43.73 39.1 17.16
Apollo found a model component of type MNL without a componentName. The name was set to "Class_2" by default.
Overview of choices for MNL model component Class_2:
alt1 alt2 alt3
Times available 2010.00 2010.0 2010.00
Times chosen 879.00 786.0 345.00
Percentage chosen overall 43.73 39.1 17.16
Percentage chosen when available 43.73 39.1 17.16
Error en apollo_weighting(P, apollo_inputs, functionality):
INTERNAL ISSUE - When applying weights at the individual level, weights should be the same for all observations of each individual.
I would really appreciate any help.