MURAL - Maynooth University Research Archive Library



    Multivariate Spatial Outlier Detection Using Robust Geographically Weighted Methods


    Harris, Paul and Brunsdon, Chris and Charlton, Martin and Juggins, Steve and Clarke, Annemarie (2014) Multivariate Spatial Outlier Detection Using Robust Geographically Weighted Methods. Mathematical Geosciences, 46 (1). pp. 1-31. ISSN 1874-8953

    [img]
    Preview
    Download (2MB) | Preview


    Share your research

    Twitter Facebook LinkedIn GooglePlus Email more...



    Add this article to your Mendeley library


    Abstract

    Outlier detection is often a key task in a statistical analysis and helps guard against poor decision-making based on results that have been influenced by anomalous observations. For multivariate data sets, large Mahalanobis distances in raw data space or large Mahalanobis distances in principal components analysis, transformed data space, are routinely used to detect outliers. Detection in principal components analysis space can also utilise goodness of fit distances. For spatial applications, however, these global forms can only detect outliers in a non-spatial manner. This can result in false positive detections, such as when an observation’s spatial neighbours are similar, or false negative detections such as when its spatial neighbours are dissimilar. To avoid mis-classifications, we demonstrate that a local adaptation of various global methods can be used to detect multivariate spatial outliers. In particular, we account for local spatial effects via the use of geographically weighted data with either Mahalanobis distances or principal components analysis. Detection performance is assessed using simulated data as well as freshwater chemistry data collected over all of Great Britain. Results clearly show value in both geographically weighted methods to outlier detection.

    Item Type: Article
    Keywords: Non-stationarity; Mahalanobis distance; Principal components analysis; Co-kriging cross-validation; Freshwater acidification; Anomaly detection;
    Academic Unit: Faculty of Science and Engineering > Research Institutes > National Centre for Geocomputation, NCG
    Item ID: 5837
    Identification Number: https://doi.org/10.1007/s11004-013-9491-0
    Depositing User: Prof. Chris Brunsdon
    Date Deposited: 17 Feb 2015 12:22
    Journal or Publication Title: Mathematical Geosciences
    Publisher: Springer Berlin Heidelberg
    Refereed: Yes
    URI:

    Repository Staff Only(login required)

    View Item Item control page

    Downloads

    Downloads per month over past year