This paper describes how neighborhood type and lifestyle are important factors influencing household and individual travel behavior. This paper presents a statistical clustering approach coupled with Geographic Information System (GIS) spatial analysis to characterize neighborhood lifestyles using sixty-four features extracted from the Census Transportation Planning Package (CTPP) 2000 data. The resulting ten clusters reveal different neighborhood lifestyles in terms of individual or household socio-economics, demographics, and land use. Travel characteristics of each cluster using the 2001 National Household Travel Survey (NHTS) travel data suggest five factors influencing household travel, socio-economic status, residential location and land use, household life cycle, activity type, and ethnics. This study has important implications to the travel demand modeling and transportation planning community. Statistical classification coupled with GIS spatial tools provides a means to associate a household with its neighborhood environment. Each neighborhood type is distinctively defined and reasonably homogenous in terms of socio-economic and travel characteristics. This not only improves travel demand prediction capability but is also more desirable when transferring travel information between geographic zones. The empirical findings from NHTS also shed lights to transportation decisions that involve the transportation-land use relationship, increasing mobility and accessibility for city low incomes, and coping with changes of travel due to demographic change.
Abstract