Online citations, reference lists, and bibliographies.
Please confirm you are human
(Sign Up for free to never see this)
← Back to Search

Exact Asymptotics For The Scan Statistic And Fast Alternatives

James Sharpnack, E. Arias-Castro
Published 2014 · Mathematics

Save to my Library
Download PDF
Analyze on Scholarcy
We consider the problem of detecting a rectangle of activation in a grid of sensors in d-dimensions with noisy measurements. This has applications to massive surveillance projects and anomaly detection in large datasets in which one detects anomalously high measurements over rectangular regions, or more generally, blobs. Recently, the asymptotic distribution of a multiscale scan statistic was established in (Kabluchko, 2011) under the null hypothesis, using non-constant boundary crossing probabilities for locally-stationary Gaussian random fields derived in (Chan and Lai, 2006). Using a similar approach, we derive the exact asymptotic level and power of four variants of the scan statistic: an oracle scan that knows the dimensions of the activation rectangle; the multiscale scan statistic just mentioned; an adaptive variant; and an epsilon-net approximation to the latter, in the spirit of (Arias-Castro, 2005). This approximate scan runs in time near-linear in the size of the grid and achieves the same asymptotic power as the adaptive scan. We complement our theory with some numerical experiments.
This paper references
Upcrossing probabilities for stationary Gaussian processes
J. Pickands (1969)
Deformable models in medical image analysis: a survey
T. McInerney (1996)
Texture detection of simulated microcalcification susceptibility effects in magnetic resonance imaging of breasts
D. James (2001)
Asymptotic properties of Gaussian random fields
C. Qualls (1973)
Scan Statistics
The emerging science of very early detection of disease outbreaks.
M. Wagner (2001)
Scan statistics
J. Glaz (2001)
An elliptic spatial scan statistic.
M. Kulldorff (2006)
A spatial scan statistic
M. Kulldorff (1997)
Optimal and fast detection of spatial clusters with scan statistics
Guenther Walther (2010)
Maximal meaningful events and applications to image analysis
A. Desolneux (2003)
Radiation detection with distributed sensor networks
S. Brennan (2004)
Extremes of the standardized Gaussian noise
Z. Kabluchko (2010)
Syndromic surveillance in public health practice, New York City.
R. Heffernan (2004)
Two moments su ce for Poisson approx-imations: the Chen-Stein method
R. Arratia (1989)
A method for detecting artificial objects in natural environments
Y. Caron (2002)
Maxima of asymptotically Gaussian random fields and moderate deviation approximations to boundary crossing probabilities of sums of random variables with multidimensional indices
H. Chan (2006)
Using the Generalized Likelihood Ratio Statistic for Sequential Detection of a Change-Point
D. Siegmund (1995)
Automatic Brain and Tumor Segmentation
Nathan Moon (2002)
The Distribution of the Size of the Maximum Cluster of Points on a Line
J. Naus (1965)
Near-optimal detection of geometric objects by fast multiscale methods
Ery Arias-Castro (2005)
Overview of sensor networks
David Cruller (2004)
On the asymptotic distribution of the discrete scan statistic
M. V. Boutsikas (2006)
Maxima of partial sums indexed by geometrical structures
Tiefang Jiang (1999)
Markov Processes, Gaussian Processes, and Local Times
M. Marcus (2006)
Evaluation of Spatial Scan Statistics for Irregularly Shaped Clusters
L. Duczmal (2006)
Detection of an anomalous cluster in a network
E. Arias-Castro (2011)
Advances in detecting and responding to threats from bioterrorism and emerging infectious disease
L. Rotz (2004)
Fire detection and growth monitoring using a multitemporal technique on AVHRR mid-infrared and thermal channels
D. Pozo (1997)

This paper is referenced by
Optimal Inference with a Multidimensional Multiscale Statistic
P. Datta (2018)
Detection of Sparse Mixtures: Higher Criticism and Scan Statistic
E. Arias-Castro (2018)
Variational estimators in statistical multiscale analysis
Housen Li (2016)
Signal Processing over graphs
James Sharpnack (2014)
Extrema of rescaled locally stationary Gaussian fields on manifolds
Wanli Qiao (2018)
On the Asymptotic Distribution of the Scan Statistic for Point Clouds
Andrew Ying (2019)
Multidimensional multiscale scanning in Exponential Families: Limit theory and statistical consequences
Claudia Konig (2018)
Template Matching and Change Point Detection by M-estimation.
Ery Arias-Castro (2020)
On Minimax Exponents of Sparse Testing
R. Mukherjee (2020)
Variational Multiscale Nonparametric Regression: Smooth Functions
M. Grasmair (2015)
Asymptotic Procedures for a Change-Point Analysis of Random Field
Béatrice Bucchia (2016)
Multiscale scanning in inverse problems
K. Proksch (2016)
Distribution du score local pour la détection de régions atypiques au sein de séquences
Sabine Mercier (2018)
Distribution-Free Detection of Structured Anomalies: Permutation and Rank-Based Scans
Ery Arias-Castro (2015)
Photonic Imaging with Statistical Guarantees: From Multiscale Testing to Multiscale Estimation
A. Munk (2020)
Extrema of locally stationary Gaussian fields on growing manifolds
Wanli Qiao (2015)
Learning Patterns for Detection with Multiscale Scan Statistics
James Sharpnack (2018)
Narrowest Significance Pursuit: inference for multiple change-points in linear models
P. Fryzlewicz (2020)
On the Asymptotic Distribution of the Scan Statistic for Empirical Distributions.
Andrew Ying (2020)
On high-dimensional support recovery and signal detection
ET Ervin Tánczos (2012)
Calibrating the scan statistic: finite sample performance vs. asymptotics
Guenther Walther (2020)
Limit laws on extremes of nonhomogeneous Gaussian random fields
Z. Tan (2017)
Semantic Scholar Logo Some data provided by SemanticScholar