Bootstrapped spatial statistics:a more robust approach to the analysis of finite strain data

Mukul, Malay and Roy, Debjani and Satpathy, Shibasis and Anil Kumar, V (2002) Bootstrapped spatial statistics:a more robust approach to the analysis of finite strain data. Technical Report. Centre for Mathematical Modelling and Computer Simulation, Bangalore, India.

Full text available as:
[img] PDF
Restricted to Archive staff only

Download (182Kb)

    Abstract

    Standard spatial statistics involves exploratory data analysis (EDA) and the computation of a semi-variogram from spatial data such as the finite strain data from a thrust sheet. However, the uncertainties in the computation of the most of the EDA and the semi-variogram parameters cannot be estimated; standard EDA allows the computation of the uncertainties associated with only the sample mean. Bootstrapped EDA is found to be more robust than the13; standard EDA because it allows uncertainties to be computed for all EDA parameters. Bootstrapped spatial statistics also allows the computation of a better and a more robust semivariogram than standard spatial statistics as the uncertainties associated with the semivariogram parameters can be ascertained. The range (a)= 750 m and sill (c) = 0.008 values associated with the exponential semi-variogram computed by Mukul (Journal of Structural Geology, 20 (4), 371-384, 1998) for the finite strain data from the Sevier fold-and-thrust belt in western USA, was recomputed using Bootstrapped Spatial Statistics. The range (a) was13; recomputed as 719.4 xB1;32.2048 and the sill (c) as 0.0097xB1; 0.0004. Kriging estimates obtained using the Bootstrapped semi-variogram indicate that the results are practically insensitive to the uncertainty associated with the estimation of parameters of the semi-variogram used.

    Item Type: Proj.Doc/Technical Report (Technical Report)
    Uncontrolled Keywords: Robust;Finite strain data
    Subjects: MATHEMATICAL AND COMPUTER SCIENCES > Statistics and Probability
    Division/Department: CSIR Centre for Mathematical Modelling and Computer Simulation, CSIR Centre for Mathematical Modelling and Computer Simulation, CSIR Centre for Mathematical Modelling and Computer Simulation, CSIR Centre for Mathematical Modelling and Computer Simulation
    Depositing User: Mr. N A
    Date Deposited: 27 Jun 2006
    Last Modified: 24 May 2010 09:44
    URI: http://nal-ir.nal.res.in/id/eprint/1868

    Actions (login required)

    View Item