Scan statistics and multiple testing in networks with applications to veterinary epidemiology
-
1
University of California, Davis, United States
-
2
University of Göttingen, Germany
Scan statistics can be used for early detection of outbreaks in animal populations by testing large regions for faint but detectable diagnostic measurements. Traditional scan statistic implementations, such as the SaTScan software [1], fuse neighboring measurements to obtain more powerful global null tests. We present computationally efficient methods and software that can utilize both spatial proximity and network information, and precisely localize the outbreak. We outline modern tools for performing scan statistics on networks, such as hierarchical multiple testing [2] and combinatorial scan statistics [3]. First, we introduce a novel false discovery rate controlling hierarchical testing procedure that is combined with hierarchical decompositions of networks such as spectral and spanning tree based decompositions. Second, we introduce a computationally efficient network scanning procedure that fuses graph neighborhood data. Finally, we demonstrate applications of these methods to syndromic surveillance using transportation networks between swine farms.
Acknowledgements
This work was also supported by NSF DMS 1712996 and NSF BIGDATA-IA 1838207.
References
[1] Kulldorff, Martin, et al. "SaTScan v 2.1: Software for the spatial and space-time scan statistics." Bethesda, MD: National Cancer Institute (1998).
[2] Sharpnack, James, Aarti Singh, and Akshay Krishnamurthy. "Detecting activations over graphs using spanning tree wavelet bases." Artificial Intelligence and Statistics. 2013.
[3] Sharpnack, James, Alessandro Rinaldo, and Aarti Singh. "Detecting anomalous activity on networks with the graph Fourier scan statistic." IEEE Transactions on Signal Processing 64.2 (2015): 364-379.
Keywords:
Scan Statistics,
False discovery rate (FDR),
Syndromic surveillance,
graph signal processing,
Hierarchical test
Conference:
GeoVet 2019. Novel spatio-temporal approaches in the era of Big Data, Davis, United States, 8 Oct - 10 Oct, 2019.
Presentation Type:
Senior oral presentation
Topic:
Spatio-temporal surveillance and modeling approaches
Citation:
Sharpnack
J,
Shemetov
D,
Proksch
K and
Martínez-López
B
(2019). Scan statistics and multiple testing in networks with applications to veterinary epidemiology.
Front. Vet. Sci.
Conference Abstract:
GeoVet 2019. Novel spatio-temporal approaches in the era of Big Data.
doi: 10.3389/conf.fvets.2019.05.00059
Copyright:
The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers.
They are made available through the Frontiers publishing platform as a service to conference organizers and presenters.
The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated.
Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed.
For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions.
Received:
01 Jun 2019;
Published Online:
27 Sep 2019.
*
Correspondence:
Mx. James Sharpnack, University of California, Davis, Davis, United States, jsharpna@ucdavis.edu