The spatial analysis of activity stop generation

Travel demand analysis is intrinsically spatial; yet spatial analysis considerations are seldom recognized and accommodated in travel modeling. The objective of this paper is to identify the spatial issues that need to be recognized in demand modeling, and to propose a multi-level, mixed logit, formulation to address these spatial issues in the context of activity stop generation. The multi-level model is estimated using the maximum simulated likelihood method. Empirical results obtained from applying the model to study shopping activity stop generation in the Boston metropolitan area are presented and discussed.