The importance of travel-time constraints in spatial choice is widely
recognized in the literature of geography and related disciplines, but
little work has been done toward developing operational models of spa
tial choice wherein these constraints and their effects are made expli
cit. The purpose of the paper is to test the accuracy of predictions p
roduced by a destination choice model that does not take explicit acco
unt of travel constraints under the assumption that observed choices a
re made from choice sets delineated by a constraint of maximum travel
time. Observed choices are generated by simulation from a new random u
tility model consistent with the constrained nature of individual choi
ce sets. Results show that the characteristics of constraints are a de
cisive factor in the accuracy of thc unconstrained choice model. Choic
e probabilities of the constrained reality are predicted with a reason
ably good accuracy in some instances, but predictions are less impress
ive, and even poor, in many others.