ApolloChoiceModelling forum

Dear authors,

thank you for building this nice package.

I would like to simulate a new choice within a logit model in Apollo. I would like to predict the aggregate market share of this new product and individual choice probabilities. I would like to do so it by altering the attributes of existing products and using the estimated parameters of the base model (with only the two original products). How can I do that? Essentially I would like to replicate example #6 from package mlogit in this link: https://cran.r-project.org/web/packages ... logit.html.

Thank you and best regards,
L

Hi

if this is just a case of changing the attribute levels for existing alternatives (rather than adding to the choice set), then this is discussed in detail in the manual and in the MNL_SP_covariates example on the apollo website - did you look at those?

Stephane

Hi Stephane,

thanks for the quick reply. Yes, I looked at those. As you say, to perturb the attributes those examples suffice. To add to the choice set I would need to think more carefully. I will come back if still needed.

Best
L

what you would need to do is to create a modified version of apollo_probabilities