OBJECTIVE: To analyze the spatial distribution of infant mortality and identify clusters with high risk of death in the first year of life. METHODS: The Thiessen (Voronoi) polygon method was used to analyze spatial distribution of the infant mortality rate, calculated by municipality. The triennium 2006 - 2008 was used as a reference to estimate the average infant mortality rate, and the first analysis of the spatial distribution of the rate was performed to test for first-order spatial stationarity. The spatial pattern was then analyzed using Moran's index and G-statistic (α = 5%). RESULTS: The surface projections on trends showed that infant mortality is not constant in space. The Moran index (0.34, P < 0.01) and G-statistic (0.03, P < 0.01) confirmed a spatial autocorrelation between infant mortality and clusters when the Thiessen polygon method was used. CONCLUSIONS: The Voronoi polygons proved accurate for spatial analysis of infant mortality and were predictive of clusters with high risk of death in the first year of life.