Untitled - UFRJ
Untitled - UFRJ
Untitled - UFRJ
You also want an ePaper? Increase the reach of your titles
YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.
Measuring Vulnerability via Spatially Hierarchical FactorModelsHedibert Freitas LopesUniversity of Chicago, USAAlexandra Mello SchmidtFederal University of Rio de Janeiro, BrazilEsther SalazarSAMSI and Duke University, USAMariana GómezUniversidad de la República, UruguayMarcel AchkarUniversidad de la República, UruguayWe address the general and challenging task of constructing social, economical, environmental orrelated indexes, as well as the specific task of constructing a model-based vulnerability index, for agiven region. We propose a new class of spatially hierarchical factor models that explicitly accountfor the different levels of hierarchy in the country, such as census tracts, municipalities, counties andcities, and that, at the same time, minimizes the loss of information inherently associated to dataaggregation. We study the Uruguayan vulnerability to vector-borne diseases and built an index thatcombines different sources of vulnerability via a set of micro-environmental indicators. We show that ourproposal outperforms current and standard approaches, which fail to properly account for discrepanciesin the region sizes, e.g. municipality or number of census tracts. We also show that data aggregationcan seriously affect the estimation of the cities vulnerability rankings under benchmark models.Keywords: Areal data, Bayesian Inference, Model Comparison, Spatial Interpolation, Spatial Smoothing.94