Important: Read this before posting to this forum

  1. This forum is for questions related to the use of Apollo. We will answer some general choice modelling questions too, where appropriate, and time permitting. We cannot answer questions about how to estimate choice models with other software packages.
  2. There is a very detailed manual for Apollo available at http://www.ApolloChoiceModelling.com/manual.html. This contains detailed descriptions of the various Apollo functions, and numerous examples are available at http://www.ApolloChoiceModelling.com/examples.html. In addition, help files are available for all functions, using e.g. ?apollo_mnl
  3. Before asking a question on the forum, users are kindly requested to follow these steps:
    1. Check that the same issue has not already been addressed in the forum - there is a search tool.
    2. Ensure that the correct syntax has been used. For any function, detailed instructions are available directly in Apollo, e.g. by using ?apollo_mnl for apollo_mnl
    3. Check the frequently asked questions section on the Apollo website, which discusses some common issues/failures. Please see http://www.apollochoicemodelling.com/faq.html
    4. Make sure that R is using the latest official release of Apollo.
  4. If the above steps do not resolve the issue, then users should follow these steps when posting a question:
    1. provide full details on the issue, including the entire code and output, including any error messages
    2. posts will not immediately appear on the forum, but will be checked by a moderator first. This may take a day or two at busy times. There is no need to submit the post multiple times.

interpretation of ICLV model estimates

Ask general questions about model specification and estimation that are not Apollo specific but relevant to Apollo users.
Post Reply
akash212
Posts: 6
Joined: 17 May 2021, 22:23

interpretation of ICLV model estimates

Post by akash212 »

Hello,

I am a beginner in choice modeling and I have created my first ICLV model (by looking at examples on the apollo website) but I am not sure how do I interpret the results. Below are my model and estimates.


apollo_beta = c(b_walk = 0,
b_bicycle = 0,
b_public_trans = 0,
b_car = 0,
b_dist_walk = 0,
b_dist_bicycle = 0,
b_dist_publictrans = 0,
b_dist_car = 0,
lambda_w = 0,
lambda_b = 0,
lambda_p = 0,
gamma_age_50 = 0,
gamma_male = 0,
gamma_nonwestern = 0,
zeta_wind_perc = 1,
zeta_prec_perc = 1,
sigma_prec_perc = 1,
sigma_wind_perc = 1
)
### Create random parameters
apollo_randCoeff=function(apollo_beta, apollo_inputs){
randcoeff = list()

randcoeff[["LV"]] = gamma_male*male + gamma_nonwestern*nonwestern + gamma_age_50*age_50 + eta

return(randcoeff)
}

### Likelihood of indicators
normalDensity_settings1 = list(outcomeNormal = precipitation_perception,
xNormal = zeta_prec_perc*LV,
mu = 0,
sigma = sigma_prec_perc,
# rows = (task==1),
componentName = "indic_prec_perc")
normalDensity_settings2 = list(outcomeNormal = wind_perception,
xNormal = zeta_wind_perc*LV,
mu = 0,
sigma = sigma_wind_perc,
# rows = (task==1),
componentName = "indic_wind_perc")


### Utility functions
V[['walk']] = (b_walk + b_dist_walk * log(dist) + lambda_w*LV )
V[['bicycle']] = ( b_bicycle + b_dist_bicycle * log(dist) + lambda_b*LV )
V[['publictrans']] = (b_public_trans + b_dist_publictrans * log(dist) + lambda_p*LV)
V[['car']] = ( b_car + b_dist_car * log(dist))

And below are my estimates.

Estimates:
Estimate s.e. t.rat.(0) Rob.s.e. Rob.t.rat.(0)
b_walk 0.2398 0.258730 0.9267 0.76719 0.3125
b_bicycle 1.2391 0.244941 5.0590 0.90280 1.3726
b_public_trans -6.8366 0.576998 -11.8487 2.34241 -2.9186
b_car 0.0000 NA NA NA NA
b_dist_walk -1.5790 0.045890 -34.4083 0.14443 -10.9328
b_dist_bicycle -0.8576 0.028998 -29.5757 0.05937 -14.4465
b_dist_publictrans 0.5128 0.045522 11.2653 0.08874 5.7790
b_dist_car 0.0000 NA NA NA NA
lambda_w -0.2419 0.160552 -1.5065 0.48544 -0.4982
lambda_b -0.7463 0.153272 -4.8689 0.57194 -1.3048
lambda_p 2.8325 0.326638 8.6716 1.35328 2.0930
gamma_age_50 0.9447 0.064021 14.7569 0.04675 20.2069
gamma_male 1.0210 0.063994 15.9548 0.04800 21.2731
gamma_nonwestern 0.9600 0.109650 8.7547 0.08290 11.5796
zeta_wind_perc 1.6564 0.040609 40.7890 0.03962 41.8075
zeta_prec_perc 1.5095 0.037215 40.5618 0.03646 41.4030
sigma_prec_perc 1.0332 0.007622 135.5676 0.01332 77.5699
sigma_wind_perc 0.8691 0.006722 129.2970 0.01530 56.7968

Could you please let me know what does positive or negative values of lambda, gamma, zeta, and sigma mean?
stephanehess
Site Admin
Posts: 974
Joined: 24 Apr 2020, 16:29

Re: interpretation of ICLV model estimates

Post by stephanehess »

Hi

this forum is mainly for questions about Apollo per se, rather than theory, and there are many papers discussing interpretation of ICLV models. More importantly, there is a detailed discussion in our journal paper (http://www.apollochoicemodelling.com/fi ... Apollo.pdf) and in the manual (http://www.apollochoicemodelling.com/files/Apollo.pdf) on how to specify, estimate and interpret ICLV in Apollo.

Stephane
--------------------------------
Stephane Hess
www.stephanehess.me.uk
akash212
Posts: 6
Joined: 17 May 2021, 22:23

Re: interpretation of ICLV model estimates

Post by akash212 »

Thank you for your guidance in the right direction.
sethyash52
Posts: 11
Joined: 09 Sep 2022, 06:38

Re: interpretation of ICLV model estimates

Post by sethyash52 »

Hi Stephane,

The link provided by you for interpreting an ICLV model needs to be fixed. Can you please resend the link?
stephanehess
Site Admin
Posts: 974
Joined: 24 Apr 2020, 16:29

Re: interpretation of ICLV model estimates

Post by stephanehess »

Hi

this forum is mainly for questions about Apollo per se, rather than theory, and there are many papers discussing interpretation of ICLV models. More importantly, there is a detailed discussion in our journal paper and in the manual on how to specify, estimate and interpret ICLV in Apollo. See the Apollo website at http://apollochoicemodelling.com/manual.html

Stephane
--------------------------------
Stephane Hess
www.stephanehess.me.uk
Post Reply