Discrete Choice Model with Structuralized Spatial Effects for Location Analysis
- 1 January 2004
- journal article
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 1898 (1) , 183-190
Abstract
The discrete choice modeling paradigm and in particular the logit model are research topics that have been continuously developed and refined for years in the field of transportation applications. Modeling locational choices, however, differ from modeling transportation choices in that geographically referenced data are used and thereby give specifically spatial choices. A discrete choice model with a systematic specification of the spatial influences in the choice process is presented. The utility function of the model is specified with autoregressive expressions for the deterministic and error components, and the model is evaluated with reference to three alternative models: the standard logit model, a logit model with an autoregressive deterministic term, and the mixed logit model with autoregressive error terms. Two applications are presented: one with simulated data and another with real data for the analysis of location choice in Sendai, Japan. The proposed model shows an improved performance over the three reference models.Keywords
This publication has 7 references indexed in Scilit:
- A mixed spatially correlated logit model: formulation and application to residential choice modelingTransportation Research Part B: Methodological, 2004
- Discrete Choice Methods with Simulation2003
- The spatial analysis of activity stop generationTransportation Research Part B: Methodological, 2002
- Mixed MNL models for discrete responseJournal of Applied Econometrics, 2000
- The Theory of Externalities, Public Goods, and Club Goods1996
- PROBIT WITH SPATIAL AUTOCORRELATIONJournal of Regional Science, 1992
- Spatial Econometrics: Methods and Models1988