[Spatial risk distribution: modeling infant mortality in Porto Alegre, Rio Grande do Sul State, Brazil]

Estimation and mapping of risk profiles are the main concerns of epidemiology. This paper analyzes spatial distribution of infant mortality cases as compared to live-born controls from Porto Alegre, Rio Grande do Sul. The modeling framework adopted in this research work is a spatial point process. Under this structure, a risk measure which continuously varies over the study region is defined and estimated using generalized additive model methods. This approach has the advantage of allowing for risk factors that are simple and easy to interpret. The procedure also allows the construction of tolerance contours which help identify areas of significantly high/low risk and an overall test for the null hypothesis of constant risk over the region. Application of this method to infant mortality data showed a highly significant spatial variation in risk for neonatal mortality data and non-significant results for post-neonatal mortality data.