Title: Spatial modelling using clustering
Authors: Jonathan Ansell - The University of Edinburgh (United Kingdom) [presenting]
Antonia Gieschen - The University of Edinburgh (United Kingdom)
Raffaella Calabrese - University of Edinburgh (United Kingdom)
Belen Martin-Barragan - The University of Edinburgh (United Kingdom)
Galina Andreeva - University of Edinburgh (United Kingdom)
Abstract: The consequences of recent work considering clustering and prediction of performance are addressed. These have both explore the spatial dependency within the domain of application. A paper dealt with the spatio-temporal clustering to explore General Practitioners (GPs) prescription behaviour across Scotland. It was based on National Health Service (NHS) Scotland Open Data which details prescription behaviour of GP. It employed ST-DBSCAN. A second paper investigated the impact of spatial behaviour in relation to performance of Small and Medium Sized Enterprises (SMEs) in the Greater London Area. The focus is on the development of appropriate measures of closeness expressed in the W matrix. The data covered a 4 year period and was modelled using a spatial probit model. Obviously, the link between the two analysis is expression of closeness across both spatial and other metrics of the individual subjects. This forms the central theme of the paper which will be discussed.