DEFINITION OF ALTERNATIVES AND REPRESENTATION OF DYNAMIC BEHAVIOR IN SPATIAL CHOICE MODELS

Abstract

This paper considers issues relevant to two important spatial-choice modeling problems: the definition of alternatives and the modeling of dynamic behavior. The definition of alternatives may benefit from the development of a classification scheme that consists of a reasonably small number of categories. This approach could lead to more manageable data requirements and improved model specification through the use of a larger set of alternative-specific constants. Also, spatial alternatives often have characteristics that do not vary from individual to individual. Recognition of this can lead to computational efficiencies and possibly easier use of aggregate data in model estimation. Dynamic behavior is modeled by introducing the effects of previous choices and using an error-components structure in the utility functions for choice models. Four special cases of the dynamic model are considered. It is then possible to identify the assumptions necessary to apply existing choice methodologies to dynamic choice problems and to recommend further research on methodologies that require less restrictive assumptions. (Author)

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 19 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.