ApolloChoiceModelling forum

Dear Sir,

Q1. I am estimating an MNL model with SP covariates, generic alternatives, and only 4 attributes. Including 'ASC' in the utility function will help me to determine which of the alternative has been chosen/preferred to be chosen by the respondents mostly? While estimating, I see a small information on the output screen:

Overview of choices for MNL model component :
Option_1 Option_2 Option_3
Times available 2976.00 2976.00 2976.0
Times chosen 886.00 1087.00 1003.0
Percentage chosen overall 29.77 36.53 33.7
Percentage chosen when available 29.77 36.53 33.7

Can I conclude by saying that Option 2 is the most preferred option by the respondents?

Q2. While including the socio-demographics and other explanatory variables, the only way to add a meaningfully interpretable model is to have the interactions for all the utility functions since the model is restricted and unlabelled. I would like to make sure that,
if I am trying to capture the information of the non EV owner (in my case EVNO with Ecar_d=0 are the non-Ev owners) having an effect on distance and charging speed or not, and the variable ' KM' (kilometer) interacts only with the price coefficient to understand the sensitivity of the price with KM (kilometer driven), the stated utility functions (script below) mentioned below is the right approach to do so?


V[['Option_1']] = b_dist * Distance_1 +b_resv * Reservation_1 + b_cost * Price_1 +
b_cpeed * Charging_Speed_1 +b_EVNOD*((Ecar_d==0)*Distance_1)+
b_EVNOS*((Ecar_d==0)*Charging_Speed_1)+b_KMP*((KM)*Price_1)

V[['Option_2']] = b_dist * Distance_2 +b_resv * Reservation_2 + b_cost * Price_2 +
b_cpeed * Charging_Speed_2 +b_EVNOD*((Ecar_d==0)*Distance_2)+
b_EVNOS*((Ecar_d==0)*Charging_Speed_2)+b_KMP*((KM)*Price_2)

V[['Option_3']] = b_dist * Distance_3 +b_resv * Reservation_3 + b_cost * Price_3 +
b_cpeed * Charging_Speed_3 +b_EVNOD*((Ecar_d==0)*Distance_3)+
b_EVNOS*((Ecar_d==0)*Charging_Speed_3)+b_KMP*((KM)*Price_3)

Yashin

1. you should always include alternative specific constants as the model makes the assumption that the mean of the error terms is the same, so you need the constants to capture the mean impact of all factors not included in the deterministic utility function. Yes, the output shows you that option 2 is chosen the most often, but that can of course be due to both observed and unobserved factors.\

2. yes, those interactions should work, but you should consider whether you want them to be linear or not

Stephane