ApolloChoiceModelling forum

Hey,

I'm trying to calculate a model with categorical variables for precipitation.
I fixed the asc for walking and the first class of precip for each mode.
As soon as I get all my betas in, the s.e. and t.ratio produces NaNs.

This is my code:


### Initialise code
apollo_initialise()

### set core controls
apollo_control = list(
modelName ="Modell_Precip_Temp_AGRGREGIERT_TAG",
modelDescr ="Simple MNL model on mode choice RP data",
indivID ="FID",
outputDirectory = "output"
)


# ################################################################# #
#### DEFINE MODEL PARAMETERS ####
# ################################################################# #

### Vector of parameters, including any that are kept fixed in estimation

apollo_beta=c(asc_fuss = 0,
asc_rad = 0,
asc_auto = 0,
asc_mitfahr = 0,
asc_oev = 0,

b_precip_fuss_0 = 0,
b_precip_fuss_1 = 0,
b_precip_fuss_2 = 0,

b_precip_rad_0 = 0,
b_precip_rad_1 = 0,
b_precip_rad_2 = 0,

b_precip_auto_0 = 0,
b_precip_auto_1 = 0,
b_precip_auto_2 = 0,

b_precip_mitfahr_0 = 0,
b_precip_mitfahr_1 = 0,
b_precip_mitfahr_2 = 0,

b_precip_oev_0 = 0,
b_precip_oev_1 = 0,
b_precip_oev_2 = 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("asc_fuss",
"b_precip_fuss_0",
"b_precip_rad_0",
"b_precip_auto_0",
"b_precip_mitfahr_0",
"b_precip_oev_0")


# ################################################################# #
#### 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[['fuss']] = asc_fuss +
b_precip_fuss_0 * (PRECIP_TAG_KAT == 0)+
b_precip_fuss_1 * (PRECIP_TAG_KAT == 1)+
b_precip_fuss_2 * (PRECIP_TAG_KAT == 2)

V[['rad']] = asc_rad +
b_precip_rad_0 * (PRECIP_TAG_KAT == 0)+
b_precip_rad_1 * (PRECIP_TAG_KAT == 1)+
b_precip_rad_2 * (PRECIP_TAG_KAT == 2)

V[['auto']] = asc_auto +
b_precip_auto_0 * (PRECIP_TAG_KAT == 0) +
b_precip_auto_1 * (PRECIP_TAG_KAT == 1) +
b_precip_auto_2 * (PRECIP_TAG_KAT == 2)


V[['mitfahr']] = asc_mitfahr +
b_precip_mitfahr_0 * (PRECIP_TAG_KAT == 0) +
b_precip_mitfahr_1 * (PRECIP_TAG_KAT == 1) +
b_precip_mitfahr_2 * (PRECIP_TAG_KAT == 2)

V[['oev']] = asc_oev +
b_precip_oev_0 * (PRECIP_TAG_KAT == 0)+
b_precip_oev_1 * (PRECIP_TAG_KAT == 1)+
b_precip_oev_2 * (PRECIP_TAG_KAT == 2)



# ################################################################# #
#### ANALYSIS OF CHOICES ####
# ################################################################# #


choiceAnalysis_settings <- list(
alternatives = c(fuss=1, rad =2, auto=4, mitfahr=5, oev=6),
avail =list(fuss =av_fuss, rad= av_rad, auto=av_auto, mitfahr = av_mitfahr, oev = av_oev),
choiceVar = choice,
V = V
)


### Compute probabilities using MNL model
P[['model']] = apollo_mnl(choiceAnalysis_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)



And these are my results:
Model name : Modell_Precip_Temp_AGRGREGIERT_TAG
Model description : Simple MNL model on mode choice RP data
Model run at : 2022-11-19 18:11:38
Estimation method : bfgs
Model diagnosis : successful convergence
Number of individuals : 1984
Number of rows in database : 100000
Number of modelled outcomes : 1e+05

Number of cores used : 1
Model without mixing

LL(start) : -151142.4
LL at equal shares, LL(0) : -151142.4
LL at observed shares, LL(C) : -122710.1
LL(final) : -122675.2
Rho-squared vs equal shares : 0.1883
Adj.Rho-squared vs equal shares : 0.1883
Rho-squared vs observed shares : 3e-04
Adj.Rho-squared vs observed shares : 2e-04
AIC : 245378.4
BIC : 245511.5

Estimated parameters : 14
Time taken (hh:mm:ss) : 00:01:27.95
pre-estimation : 00:00:18.59
estimation : 00:00:14.57
post-estimation : 00:00:54.79
Iterations : 25
Min abs eigenvalue of Hessian : 1e-06
Some eigenvalues of Hessian are positive, indicating potential problems!

Unconstrained optimisation.

These outputs have had the scaling used in estimation applied to them.
Estimates:
Estimate s.e. t.rat.(0) Rob.s.e. Rob.t.rat.(0)
asc_fuss 0.00000 NA NA NA NA
asc_rad -0.50569 0.02406 -21.02 0.06669 -7.58274
asc_auto 1.18131 0.01752 67.41 0.04961 23.81087
asc_mitfahr -0.47686 0.02103 -22.67 0.05287 -9.01947
asc_oev -0.97220 0.02485 -39.12 0.06137 -15.84059
b_precip_fuss_0 0.00000 NA NA NA NA
b_precip_fuss_1 0.05050 492.93528 1.0244e-04 NaN NaN
b_precip_fuss_2 0.06223 NaN NaN 0.15710 0.39613
b_precip_rad_0 0.00000 NA NA NA NA
b_precip_rad_1 -0.12342 492.93528 -2.5038e-04 NaN NaN
b_precip_rad_2 -0.12571 NaN NaN 0.25779 -0.48766
b_precip_auto_0 0.00000 NA NA NA NA
b_precip_auto_1 0.03870 492.93528 7.851e-05 NaN NaN
b_precip_auto_2 0.07110 NaN NaN 0.33047 0.21515
b_precip_mitfahr_0 0.00000 NA NA NA NA
b_precip_mitfahr_1 0.05703 492.93527 1.1569e-04 NaN NaN
b_precip_mitfahr_2 -0.03169 NaN NaN NaN NaN
b_precip_oev_0 0.00000 NA NA NA NA
b_precip_oev_1 -0.02281 492.93527 -4.627e-05 NaN NaN
b_precip_oev_2 0.02407 NaN NaN 0.33292 0.07231



Thanks for your help!
Pia

Hi

your model is overspecified. You cannot interact the covariate with all of the alternatives, i.e. you need keep the terms b_precip_fuss_1 and b_precip_fuss_2 fixed to 0 too

Stephane