UCL  IRIS
Institutional Research Information Service
UCL Logo
Please report any queries concerning the funding data grouped in the sections named "Externally Awarded" or "Internally Disbursed" (shown on the profile page) to your Research Finance Administrator. Your can find your Research Finance Administrator at https://www.ucl.ac.uk/finance/research/rs-contacts.php by entering your department
Please report any queries concerning the student data shown on the profile page to:

Email: portico-services@ucl.ac.uk

Help Desk: http://www.ucl.ac.uk/ras/portico/helpdesk
Publication Detail
Spatio-temporal autocorrelations of networks and their implications for space-time modelling
  • Publication Type:
    Conference presentation
  • Publication Sub Type:
    Presentation
  • Authors:
    Haworth J, CHENG T
  • Date:
    2011
  • Status:
    Published
  • Name of Conference:
    Annual Meeting of the Association of American Geographers
  • Conference place:
    Seattle, USA
  • Conference start date:
    12/04/2011
  • Conference finish date:
    16/04/2011
  • Keywords:
    temporal, spatial, spatio-temporal, transportation, network complexity
Abstract
With improvements in data collection and storage methods and increased computing power, large scale network datasets with high spatial and temporal resolutions are now becoming available to researchers. This creates fresh challenges regarding the extraction of meaningful information from such data. One of the problems, and perhaps benefits, of data collected on a network is the presence of spatial, temporal and spatio-temporal autocorrelation between observations, which violates the assumption of stationarity and leads to model misspecification. Consequently, over the years a number of space-time models have been developed to account for the effects of autocorrelation. These models often use parameter estimates that are fixed spatially and/or temporally. However, few studies to date have focussed on network data with extremely high temporal resolution; on such networks the autocorrelation structure is likely to be dynamic in space and time. Using the case study of travel time data collected by Transport for London in London, UK, this paper investigates the network autocorrelation structure of a road network using global and local spatial, temporal and spatio-temporal autocorrelation analysis. The findings are twofold; firstly, the structure is found to be dynamic in both space and time, which has implications for space-time models based on globally fixed parameter estimates. Secondly, commonly used global indicators of spatial and spatio-temporal autocorrelation are found to mask the local variations in the autocorrelation structure of the network. Finally, traffic flow theory is used to describe a possible relationship between traffic conditions, magnitude of autocorrelation and range of autocorrelation
Publication data is maintained in RPS. Visit https://rps.ucl.ac.uk
 More search options
UCL Researchers
Author
Dept of Civil, Environ &Geomatic Eng
University College London - Gower Street - London - WC1E 6BT Tel:+44 (0)20 7679 2000

© UCL 1999–2011

Search by