Pushing Them to the Edge: an Assessment of Spatial Microsimulation Methods

This paper will look at how well a spatial microsimulation model handles additional constraints, and how results from univariate constraint tables rather than multivariate constraint tables compare. This paper will also test how well non-Capital city households from a survey can estimate areas within capital cities. The argument for this approach is that the spatial microsimulation method has more households to choose from to represent the constraints in the area being estimated. In theory, this should improve the fit of the model. However, the alternative argument that could be made is that a household from another area may not be representative of households in the area being estimated – so, for example, in Australia, households in remote New South Wales will not be representative of households in Sydney. This paper aims to check the appropriateness of using households from anywhere in Australia to estimate SLAs in capital cities by running each model both ways (so using all households to estimate small areas in Sydney; and then using Sydney households to estimate small areas in Sydney), and comparing and contrasting the results. The data used in the model is Australian Census and survey data from the Australian Bureau of Statistics (ABS).