Portal de Periódicos da CAPES

Developing a Continuous Space Representation of a Simulated Population

2010; Routledge; Volume: 5; Issue: 3 Linguagem: Inglês

10.1080/17421772.2010.493954

1742-1780

John Cullinan,

Insurance, Mortality, Demography, Risk Management

Spatial microsimulation models typically match census of population data with survey data in order to simulate synthetic populations of individuals and households within small-scale geographic areas. For most spatial microsimulation applications this level of spatial precision is satisfactory. For others, more precise information on the location of simulated units may be required. To this end this paper develops a continuous space representation of a simulated population. It presents a statistical matching approach for assigning simulated households from a spatial microsimulation model to unique spatially-referenced residential locations. The allocation is based on a random assignment after splitting the simulated households into two groups: those predicted to reside in apartments and those predicted to reside in houses. The resulting ‘geohouseholds’ have a range of potential applications in economic and spatial analysis. Création d'une représentation spatiale continue d'une population stimulée Résumé Les modèles de microsimulation spatiale assortissent généralement les données de recensement de la population à des données de sondages, afin de simuler des populations synthétiques de particuliers et de foyers au sein de régions géographiques à échelle restreinte. Dans la plupart des applications de microsimulation spatiale, ce niveau de précision spatiale est satisfaisant. Dans d'autres, des informations plus précises sur l'emplacement d'unités simulées pourront s'avérer nécessaires. A cette fin, la présente communication crée une représentation spatiale continue d'une population simulée. Elle présente une méthode de correspondance statistique permettant d'affecter des foyers simulés, issus d'un modèle de microsimulation spatiale à des lieux résidentiels unique à référence spatiale. Cette allocation est basée sur une affectation aléatoire après la subdivision des foyers simulés en deux groupes : ceux dont on prévoit qu'ils résideront en appartement, et ceux dont on prévoit qu'ils résideront dans un maison. Les « géofoyers » résultants présentent toute une série d'applications potentielles pour les analyses économiques et spatiales. Desarrollo de una representación espacial continua de una población simulada Extracto Típicamente, los modelos de microsimulación espacial emparejan el censo de datos de la población con datos de encuestas, con objeto de simular poblaciones sintéticas de individuos y hogares dentro de áreas geográficas a pequeña escala. Para la mayoría de las aplicaciones de microsimulación espacial este nivel de precisión espacial es satisfactorio. Para otras, podría requerirse información más precisa sobre la ubicación de unidades simuladas. Con este objetivo, este trabajo desarrolla la representación espacial continua de una población simulada. Presenta un planteamiento de emparejamiento estadístico para asignar hogares simulados procedentes de un modelo de microsimulación espacial a ubicaciones residenciales únicas referenciadas espacialmente. La colocación se basa en una asignación al azar después de dividir los hogares simulados en dos grupos: los que se predice que residirán en apartamentos y los que se predice que residirán en casas. Los ‘geohogares’ resultantes ofrecen una gama de aplicaciones en potencia en el análisis económico y espacial. Keywords: Spatial microsimulationstatistical matchingspatial analysisrecreation demand modellingJEL classification : R2C63Q26 Acknowledgements The author wishes to thank Stephen Hynes, Cathal O'Donoghue, Eoghan Garvey and the two anonymous referees, as well as seminar participants at the Regional Science Association International: British and Irish Section 39th Annual Conference, Limerick, September 2009, the European Association of Environmental and Resource Economists Annual Conference, Amsterdam, June 2009 and the Irish Economic Association Annual Conference, Blarney, April 2009 for useful comments on an earlier version of this paper. Support from Teagasc under the Walsh Fellowship Scheme is gratefully acknowledged. Notes 1. In Ireland, small area population statistics at electoral division level are routinely used to conduct spatio-economic analysis. However, the problems associated with using Irish EDs for spatial analysis are well-known. Indeed, according to Foley et al. (Citation2005), ‘the current smallest areal unit available at national level, the Electoral Division …, is unsatisfactory’. See Cullinan (2008) for more details. 2. The GeoDirectory data used in this paper are based in part on remotely sensed data. 3. The second process, known as the dynamic process, ages the population by simulating life cycle characteristics such as demographics, labour market outcomes and migration patterns and is discussed in Kelly (Citation2004b). 4. The IPF procedure has been used to generate a number of spatial microsimulation models. However, one of the most difficult tasks related to this approach is specifying which variables depend on which others, as well as determining the ‘ordering’ of probabilities (Ballas & Clarke, Citation2003). 5. SMILE also contains a number of internal validation measures, including z-scores and z 2-scores. See Kelly (Citation2004a) for a full description. 6. The process illustrated in Figure 1 is similar to one presented in Ballas et al. (Citation2007) for Micro-MaPPAS, a spatial microsimulation modelling and predictive policy analysis system. Like SMILE, Micro-MaPPAS includes a restart facility to allow for further searching. Unlike SMILE however, it also allows the user to indicate whether particular census variables are more important than others and to weight them accordingly. 7. The number of households per ED within SMILE ranges from 17 to 7,859, at an average of 376.4 households. 8. One possibility is to assume that each household resides at the geographic centroid of each ED (dots in Figure 2) or at some population-weighted centroid. 9. While all urban EDs contained apartments, a number of rural EDs did not, meaning that the allocation is essentially random for these EDs. This is a weakness in the approach but can easily be addressed with more comprehensive data. 10. A number of other explanatory variables were considered, including the marital status and employment status of the head of household. The latter was found to be highly correlated with the income variable used and consequently did not add to the overall explanatory power of the model. Variables relating to the region or location type of the household were excluded, since the aim here is to allocate households within a particular ED across that ED. Therefore, location dummies are not required since SMILE households are already assigned to an ED. 11. See O'Donoghue et al. (Citation2009) for more details. 12. For more details, see O'Donoghue et al. (Citation2009). 13. As previously stated, however, Ballas & Clarke (Citation2003) did not undertake such a modelling exercise. 14. The second principal potential benefit of matching locations and simulated households outlined by Ballas & Clarke (Citation2003) relates to the potential for business applications. It would be useful to know, for example, ‘where particular household distributions are within the ED so that particular streets or blocks of streets could be targeted (say for postal mail shots) rather than every household in the ED’. Finally, the third benefit relates to the increased potential of remotely sensed data, such as putting ‘estimations on the types of buildings in terms of housing types and characteristics of their inhabitants. Clearly, it is not possible to categorically say what types of families were in each building. However, it may be possible to give an estimation of the types of families within blocks thus giving very detailed portraits of small areas of our cities’. 15. Cullinan (2008 also used the same general modelling approach in an environmental value transfer context to estimate the potential amenity value of prospective new ‘policy’ forest recreation sites in Ireland.