A binary logistic model was developed to understand the probability
of users’ to recommend the service to others. Table 3 presents
the results of the model which contains 440 observations and
explains about 31% of the variation in users’ willingness to recommend
the service to others. Regarding the key policy variables, the
model indicates that users’ satisfaction with service attributes
increases the odds of being willing to recommend the service. Users
who are satisfied with their waiting time are 3.32 times more likely
to recommend the service compared to other users who are not satisfied
with their waiting time. Therefore, transit agencies should
work on improving users waiting time satisfaction in order to
increase their willingness to recommend the service to others. In
addition, being satisfied with the trip’s travel time and experience
on board also have a statistically significant impact on users’ willingness
to recommend the service to others. Users who are satisfied
with travel time are 2.7 times more likely to recommend the service
to others compared to those who are unsatisfied with travel time. In
addition, those who are satisfied with the experience on board are
1.97 times more likely to recommend the service compared to those
who are unsatisfied with the on board experience. Satisfaction with
the cost of the trip did not show a significant impact on the odds of recommending the service to others. In other words, the more satisfied
a person is with his or her waiting and travel time, the more
likely he or she becomes to recommend the service to others. Therefore,
transit agencies should implement various improvement
strategies in order to keep and increase users’ satisfaction with their
waiting and travel time, and to a lesser degree, strategies that
improve uses’ experience onboard.