I have a mixed logit model with travel cost, travel time, and mode constants. If I only randomize travel cost and keep fixed coefficients for travel time and mode constants, will the model capture overall unobserved heterogeneity or just the randomness observed in travel cost?

So if I want to capture unobserved heterogeneity due to age, gender, etc., do I have to randomize the mode constant, or that is captured in the distribution I assumed for the travel cost.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.