Reference : Surveying activity-travel behavior in Flanders: Assessing the impact of the survey design
Scientific congresses and symposiums : Paper published in a book
Engineering, computing & technology : Civil engineering
Business & economic sciences : Special economic topics (health, labor, transportation…)
http://hdl.handle.net/2268/134173
Surveying activity-travel behavior in Flanders: Assessing the impact of the survey design
English
Cools, Mario mailto [Universiteit Hasselt - UH > > > >]
Moons, Elke [Universiteit Hasselt - UH > > > >]
Bellemans, Tom [Universiteit Hasselt - UH > > > >]
Janssens, Davy [Universiteit Hasselt - UH > > > >]
Wets, Geert [Universiteit Hasselt - UH > > > >]
2009
Proceedings of the BIVEC-GIBET Transport Research Day 2009, Part II
Macharis, C.
Turcksin, L.
VUBPress
727-741
Yes
No
International
Brussels
Belgium
BIVEC-GIBET Transport Research Day 2009
27-05-2009
BIVEC-GIBET
Brussels
Belgium
[en] activity-travel behavior ; mixed-mode survey design ; heteroscedastic linear regression
[en] Ever since car ownership and car use started to increase in Western Europe and the USA, transportation planners attempted to model people’s travel behavior. In the context of the Feathers project a dynamic activity-based travel demand framework is developed for Flanders. In this paper, the complete survey design of the data collection effort required for such dynamic activity-based model is discussed. A mixed survey design of using a PDA application on the one hand, and using traditional paper and pencil diaries on the other hand, turns out to be a very suitable way of collecting detailed information about planned and executed activity-travel behavior of households. The results show that no attrition effects are present, not on the number of out-of-home activities reported, nor on the number of trips reported. Moreover the survey mode (PDA versus paper and pencil) has no direct impact on the quantities investigated. Notwithstanding, it is essential for further analysis on the Feathers data to explicitly take into account mode effects because of two reasons. First, the effect of explanatory variables can be influenced by the survey mode. Second, the variance in the estimation of the quantity investigated can differ significantly. Heteroscedatisc linear regression models provide the required framework to explicitly take into account these mode effects.
Lepur : Centre de Recherche sur la Ville, le Territoire et le Milieu rural ; LEMA - Local Environment Management and Analysis
Researchers ; Professionals ; Students ; General public ; Others
http://hdl.handle.net/2268/134173

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
BIVEC2009 Cools-Moons-Bellemans-Janssens-Wets.pdfAuthor postprint205.45 kBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.