Using hazard-based models to explain changes in the duration of journey-to-work trips

  1. Lookup NU author(s)
  2. Aziza Safour
  3. Dr Dilum Dissanayake
  4. Professor Margaret Carol Bell CBE
  5. Dr Neil Thorpe
Author(s)Safour A, Dissanayake D, Bell MC, Thorpe N
Editor(s)Universities' Transport Studies Group
Publication type Conference Proceedings (inc. Abstract)
Conference Name41st Annual UTSG Conference
Conference LocationLondon
Year of Conference2009
Legacy Date7-9 January 2009
VolumeCD-ROM
Pages
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
This study aims to contribute to the area of activity-based travel modelling by investigating household daily activity patterns using hazard-based duration models. Recent studies have shown that hazard models could be a powerful tool for activity modelling. The analysis investigates changes in household activity patterns during the weekdays. The models use data from the Tyne and Wear household travel survey conducted between 2003 and 2007. The database consists of travel related activities and individual and household information. Parametric hazard models are chosen to analyse the data. The models are fitted to the data and the fitness is evaluated using adjusted Anderson-Darling test statistics and correlation coefficients. A regression analysis is conducted to capture the impact of individuals’ and households’ socio-demographic characteristics and location and trip making characteristics on the hazard rate of duration of different activities. The early results indicate that the hazard function of different activities possesses similar trends of activity patterns. However, the highest rate of hazard is on the first year followed by the second year of the survey. The parameters indicate that the various activity durations have been affected by the trip-making characteristics more than other characteristics, for example home-based trips have the greatest rate comparing with the other trips.
PublisherUniversities' Transport Studies Group