Cançado, André Luiz FernandesGomes, Antonio E.Silva, Cibele Queiroz daOliveira, Fernando Luiz Pereira deDuczmal, Luiz Henrique2018-01-302018-01-302016CANÇADO, A. L. F. et al. An item response theory approach to spatial cluster estimation and visualization. Environmental and Ecological Statistics, v. 23, p. 1-17, 2016. Disponível em: <https://link.springer.com/article/10.1007/s10651-016-0347-x>. Acesso em: 16 jan. 2018. 1573-3009 http://www.repositorio.ufop.br/handle/123456789/9384The scan statistic is widely used in spatial cluster detection applications of inhomogeneous Poisson processes. The most popular variant of the spatial scan is the circular scan. However, such approach has several limitations, in particular, the circular window is not suitable to make the correct description of irregularly shaped and/or unconnected clusters. Additionally, such methodology does not incorporate the tools needed for quantifying the uncertainty in the description of the most likely cluster in the analysis. In the present work we build upon the previously proposed methodology called intensity function a more efficient and accurate way of defining the uncertainty in the identification of spatial clusters using Item Response Theory ideas. Using simulated data we show that the proposed method can correctly identify primary, secondary and irregular clusters.en-USrestritoInhomogeneous poisson processItem response theoryIrregularly shaped spatial clustersScan statisticArtigo publicado em periodicohttps://link.springer.com/article/10.1007/s10651-016-0347-xhttps://doi.org/10.1007/s10651-016-0347-x