Modelling spatially varying impacts of socioeconomic predictors on mortality outcomes

A methodology is proposed for modelling spatially varying predictor effects on a disease or mortality count outcome. The methodology may be extended to multivariate outcomes, so that one may assess the similarity of spatial patterning of regression effects between outcomes. Another extension involves longitudinal data, where a number of modelling structures are possible. The methodology is illustrated by suicide mortality in 32 London Boroughs over the period 1979–1993, in terms of area deprivation and a measure of social fragmentation. Copyright Springer-Verlag Berlin Heidelberg 2003