Accommodating Spatial Correlation Across Choice Alternatives in Discrete Choice Models: Application to Modeling Residential Location Choice Behavior

This paper presents a modeling methodology capable of accounting for spatial correlation across choice alternatives in discrete choice modeling applications. Many location choice (e.g., residential location, workplace location, destination location) modeling contexts involve choice sets where alternatives are spatially correlated with one another. In the presence of spatial correlation, traditional discrete choice modeling methods that are often based on the assumption of independence among choice alternatives are not appropriate. Previous work in the field has yielded methods that can accommodate correlation among neighboring or adjacent location choices, but has not provided the ability to accommodate spatial correlations that may exist across choice alternatives that are not necessarily neighbors or adjoining one another. In this paper, a generalized spatially correlated logit (GSCL) model, and its mixed version, that allows one to represent the degree of spatial correlation as a function of a multidimensional vector of attributes characterizing each pair of location choice alternatives is formulated and presented. The model is applied to the analysis of residential location choice behavior using a sample of households drawn from the 2000 San Francisco Bay Area Travel Survey (BATS) data set. Model estimation results obtained from the GSCL are compared against those obtained using the standard multinomial logit (MNL) model and the spatially correlated logit (SCL) model where only correlations across neighboring (or adjacent) alternatives are accommodated. Model findings suggest that there is significant spatial correlation across alternatives that do not share a common boundary, and that the GSCL offers the ability to more accurately capture spatial location choice behavior.

• Corporate Authors:

  Transportation Research Board

  500 Fifth Street, NW
  Washington, DC  United States  20001
• Authors:
  • Sener, Ipek Nese
  • Pendyala, Ram M
  • Bhat, Chandra R
  • 0000-0002-0715-8121
• Conference:
  • Transportation Research Board 88th Annual Meeting
  • Location: Washington DC, United States
  • Date: 2009-1-11 to 2009-1-15
• Date: 2009

Language

• English

Media Info

• Media Type: DVD
• Features: References; Tables;
• Pagination: 24p
• Monograph Title: TRB 88th Annual Meeting Compendium of Papers DVD

Subject/Index Terms

• TRT Terms: Alternatives analysis; Choice models; Multinomial logits; Public transit; Residential location; Spatial analysis; Transit operating agencies; Travel surveys
• Uncontrolled Terms: Discrete choice
• Geographic Terms: San Francisco Bay Area
• Subject Areas: Highways; Passenger Transportation; Planning and Forecasting; Public Transportation; I72: Traffic and Transport Planning;

Filing Info

• Accession Number: 01128747
• Record Type: Publication
• Report/Paper Numbers: 09-2281
• Files: TRIS, TRB
• Created Date: May 19 2009 7:48AM