Abstract
In this paper Australian domestic and international inbound travel are modelled by an anisotropic dynamic spatial lag panel Origin-Destination (OD) travel flow model. Spatial OD travel flow models have traditionally been applied in a single cross-sectional context, where the spatial structure is assumed to have reached its long run equilibrium and temporal dynamics are not explicitly considered. On the other hand, spatial effects are rarely accounted for in traditional tourism demand modelling. We attempt to address this dichotomy between spatial modelling and time series modelling in tourism research by using a spatial-temporal model. In particular, tourism behaviour is modelled as travel flows between regions. Temporal dependencies are accounted for via the inclusion of autoregressive components, while spatial autocorrelations are explicitly accounted for at both the origin and the destination. We allow the strength of spatial autocorrelation to exhibit seasonal variations, and we allow for the possibility of asymmetry between capital-city neighbours and non-capital-city neighbours. Significant temporal and spatial dynamics have been uncovered for both domestic and international tourism demand. For example we find strong seasonal temporal autocorrelations, significant trends and significant spatial autocorrelations at both the origin and the destination. Moreover, the spatial patterns are found to be most significant during peak holiday seasons. Understanding these patterns in tourist behaviour has important implications for tourism operators.
Highlights
In two of the most recent and comprehensive reviews on tourism demand modelling and forecasting, Li et al (2005) and Song & Li (2008) fail to identify any substantial studies using spatial methods
We argue that spatial patterns in tourism demand are best interpreted as results of substantive human interaction, a spatial lag specification is favoured over a spatial error specification
Our international inbound data comes from the International Visitor Survey (IVS), which is a quarterly survey of approximately 20,000 international tourists at points of departure from Australia each year
Summary
In two of the most recent and comprehensive reviews on tourism demand modelling and forecasting, Li et al (2005) and Song & Li (2008) fail to identify any substantial studies using spatial methods. We model Australian domestic and international inbound tourism demand using a dynamic spatial panel Origin-Destination (OD) travel flow model. In dealing with dynamic panels, difficulties arise due to the correlation between lagged dependent variables and time-invariant individual effects.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
