Geostatistical models are widely used to describe the structure of the spatial function in many areas of hydrosciences and environmental engineering. A model developed for geostatistical estimation must be tested against field data to check its validity. Orthonormal residuals as a diagnostic tool have advantages over conventional standardized residuals in that they are easy to calculate and the determination of the sampling distributions of statistics based on them is computationally efficient. In this paper, the applicability of two test methods based on orthonormal residuals is studied. For a set of groundwater head measurements, two different models of the structure of the head field are tested. Results indicate that two tests agree with each other and thus can be used for diagnosing model adequancy.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Geostatistical model validation using orthonormal residuals


    Additional title:

    KSCE J Civ Eng


    Contributors:

    Published in:

    Publication date :

    1997-12-01


    Size :

    8 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    Regularization of orthonormal vector sets using coupled PDE's

    Tschumperle, D. / Deriche, R. | IEEE | 2001


    Regularization of Orthonormal Vector Sets Using Coupled PDE's

    Tschumperle, D. / Deriche, R. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2001


    LEGAL - RESIDUALS: VANS

    Online Contents | 2004


    Damage Detection Using Expanded Dynamic Residuals

    Zimmerman, D. / Kim, H. / Bartkowicz, T. et al. | British Library Conference Proceedings | 1996


    Damage detection using expanded dynamic residuals

    Zimmerman, David / Kim, Hyoung / Bartkowicz, Theodore et al. | AIAA | 1998