7.4. Travel Example

Now let’s look at a more complicated application of the conditional logit model. In a survey of transportation usage between three Australian cities, 210 people were asked which of four options they used on their most recent trip: air, train, bus, or car (Hensher and Bradley 1993). They were also asked about certain characteristics of all four travel options, regardless of whether they used them. As in the previous example, a separate observation is constructed for each option for each person, giving a total of 840 observations. The variables are:

IDA unique identifier for each person
MODE1=air, 2=train, 3=bus, 4=car
CHOICE1=chose that mode, 0=didn’t choose
TIMETerminal waiting time
COSTTotal cost for all stages
TIMETotal time ...

Get Logistic Regression Using SAS®: Theory and Application now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.