Discrete choice analysis has become an industry standard in land use and transportation models. Such models are fundamentally grounded in individual choice; therefore, the treatment of interdependencies among decision makers is a formidable challenge. Through an empirical application to mode choice, the capture of interdependencies in discrete choice is described and illustrated. Decision makers are assumed to be influenced, for example, by people of similar socioeconomic status who are nearby. Given such social and spatial network relationships, the choice model captures interdependencies in two ways: (a) including in the systematic utility variables that describe choices of others in the decision maker's social and spatial network and (b) allowing for correlation across the disturbances of decision makers within the same social and spatial network. Variations of these approaches (including their combination and the use of random parameters) are tested with mode choice and compared with traditional methods of market segmentation. The application results indicate that the proposed methods for capturing interdependencies are significant and superior to traditional methods. Furthermore, capturing the interdependencies in the systematic utility is sufficient: it is better than the model with just correlation and is not significantly worse than the model with both the systematic term and correlation. The systematic term also captures a feedback effect that can propel the adoption of a new mode over time, for example. Models are estimated with the use of a traditional transportation data set and readily available software.
