Optimal and fast detection of spatial clusters with scan statistics
From MaRDI portal
Publication:2380095
Abstract: We consider the detection of multivariate spatial clusters in the Bernoulli model with locations, where the design distribution has weakly dependent marginals. The locations are scanned with a rectangular window with sides parallel to the axes and with varying sizes and aspect ratios. Multivariate scan statistics pose a statistical problem due to the multiple testing over many scan windows, as well as a computational problem because statistics have to be evaluated on many windows. This paper introduces methodology that leads to both statistically optimal inference and computationally efficient algorithms. The main difference to the traditional calibration of scan statistics is the concept of grouping scan windows according to their sizes, and then applying different critical values to different groups. It is shown that this calibration of the scan statistic results in optimal inference for spatial clusters on both small scales and on large scales, as well as in the case where the cluster lives on one of the marginals. Methodology is introduced that allows for an efficient approximation of the set of all rectangles while still guaranteeing the statistical optimality results described above. It is shown that the resulting scan statistic has a computational complexity that is almost linear in .
Recommendations
Cites work
- A spatial scan statistic
- Asymptotically exact nonparametric hypothesis testing in sup-norm and at a fixed point
- Clustering of Random Points in Two Dimensions
- scientific article; zbMATH DE number 1405929 (Why is no real title available?)
- scientific article; zbMATH DE number 3249395 (Why is no real title available?)
- scientific article; zbMATH DE number 2243369 (Why is no real title available?)
- Large-deviation approximations to the distribution of scan statistics
- Multiscale inference about a density
- Multiscale testing of qualitative hypotheses
- On the Distributions of Scan Statistics of a Two-Dimensional Poisson Process
- Probability Inequalities for Sums of Bounded Random Variables
- Scan statistics
- Scan statistics and applications
- Two-dimensional discrete scan statistics
Cited in
(51)- FDR-control in multiscale change-point segmentation
- Variational multiscale nonparametric regression: smooth functions
- Wald-based spatial scan statistics for cluster detection
- Detecting Markov random fields hidden in white noise
- Multiscale blind source separation
- Cluster detection in networks using percolation
- A multivariate Bayesian scan statistic for early event detection and characterization
- Multiscale scanning in inverse problems
- Optimal inference with a multidimensional multiscale statistic
- Anomaly detection: a functional analysis perspective
- Tail bounds for empirically standardized sums
- Large-scale inference with block structure
- Spatial and temporal clustering based on the echelon scan technique and software analysis
- Multidimensional multiscale scanning in exponential families: limit theory and statistical consequences
- Multiscale change-point segmentation: beyond step functions
- Hotspot detection with bivariate data
- Detection of an anomalous cluster in a network
- TEAM: a multiple testing algorithm on the aggregation tree for flow cytometry analysis
- Optimal detection of a jump in the intensity of a Poisson process or in a density with likelihood ratio statistics
- Detecting a path of correlations in a network
- Localizing differentially evolving covariance structures via scan statistics
- Exact asymptotics for the scan statistic and fast alternatives
- Clustering with exclusion zones: genomic applications
- Analysis of Distributional Variation Through Graphical Multi-Scale Beta-Binomial Models
- Interpretable clustering using unsupervised binary trees
- Change-point model on nonhomogeneous Poisson processes with application in copy number profiling by next-generation DNA sequencing
- scientific article; zbMATH DE number 1405929 (Why is no real title available?)
- Distribution-free detection of structured anomalies: permutation and rank-based scans
- Discovery of anomalous spatio‐temporal windows using discretized spatio‐temporal scan statistics
- Structured correlation detection with application to colocalization analysis in dual-channel fluorescence microscopic imaging
- Asymptotic properties of spatial scan statistics under the alternative hypothesis
- Computing approximate statistical discrepancy
- Detecting clusters with increased mean using scan windows with variable radius
- BET on independence
- Fisher Exact Scanning for Dependency
- An Alternative Cluster Detection Test in Spatial Scan Statistics
- Spatial scan statistics for detection of multiple clusters with arbitrary shapes
- Fast subset scan for spatial pattern detection
- Multiscale change point inference. With discussion and authors' reply
- Identifying the support of rectangular signals in Gaussian noise
- Detecting structured signals in Ising models
- Anomaly Detection for a Large Number of Streams: A Permutation-Based Higher Criticism Approach
- Optimal calibration for multiple testing against local inhomogeneity in higher dimension
- Instrument Validity Tests With Causal Forests
- Multiscale tests for point processes and longitudinal networks
- Multiscale scanning with nuisance parameters
- Fast subset scan for multivariate event detection
- Sparse anomaly detection across referentials: a rank-based higher criticism approach
- Optimal confidence bands for shape-restricted regression in multidimensions
- Optimal detection of multi-sample aligned sparse signals
- Spatial multiresolution cluster detection method
This page was built for publication: Optimal and fast detection of spatial clusters with scan statistics
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2380095)
