Modeling the relationship between perceived neighbourhood characteristics and adult hospitalization frequencies from a cross-sectional study

Interest in the quantitative effects of neighbourhood characteristics on urban health has recently increased in social epidemiology.Such effects are mostly stydied employing multilevel models based on some definition of neighbourhood. We investigate the statistical relationship between health and the neighboururhood quality as perceived by individuals, thus avoiding the inconvenient of choosing a specific administrative definition. We use sampling data from the Los Angels Family and Neighb. Survey(L.A.FANS). We choose the number of hospitalizations in the last two years as health status and we have related this number to several individual characteristics through Generalized Additive Models(GAM),focusing on Zero Inflated Poisson(ZIP) , which are unusual choices in this context. We also overcome to some extent the difficulties in interpreting the results from a GAM with a ZIP distribution by simulating predicted values under varying assumptions in order to reveal the relationship of interest.The analyses confirm results already published in the literature , suggesting also that new opportunities , from a statistical methods point of view, are available in this specific field of social epidemiology.