Upper level set scan statistic for detecting arbitrarily shaped hotspots

By Ganapati P. Patil, Charles Taillie. Environmental and Ecological Statistics, 2004

296 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Spatio-temporal exceedance locations and confidence regions (2013, methodology): “Patil and Taillie (2004) used the upper level set (ULS) scan statistic, a modification of the popular spatial scan statistic [Kulldorff and Nagarwalla (1995); Kulldorff (1997)] to identify regions or clusters of cells with elevated responses when compared to neighboring cells.”
Weighted Normal Spatial Scan Statistic for Heterogeneous Population Data (2009, methodology): “With more flexible search window (Patil and Taillie 2004; Tango and Takahashi 2005; Kulldorff et al. 2006), we could have better precision in the location of the true clusters.”
Tests of Spatial Randomness Adjusted for an Inhomogeneity (2006, unknown): “…cluster tests (Alexander et al. 1991, p. 166), the Ord–Getis max Gi (Ord and Getis 1995, p. 296), the Patil–Taillie upper-level set scan statistics (Patil and Taillie 2003, 2004), the simulated annealing scan statistic (Duczmal and Assunção 2004; Duczmal, Kulldorff, and Huang 2006), the…”
Spatial Cluster Analysis (2008, methodology): “The first method, called the Upper Level Set scan statistic (Patil and Taillie 2004), involves estimation of cluster morphology (e.g. shape, extent and configuration) from the data itself.”