skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Book Review Geostatistical Analysis of Compositional Data

Abstract

Compositional data are represented as vector variables with individual vector components ranging between zero and a positive maximum value representing a constant sum constraint, usually unity (or 100 percent). The earth sciences are flooded with spatial distributions of compositional data, such as concentrations of major ion constituents in natural waters (e.g. mole, mass, or volume fractions), mineral percentages, ore grades, or proportions of mutually exclusive categories (e.g. a water-oil-rock system). While geostatistical techniques have become popular in earth science applications since the 1970s, very little attention has been paid to the unique mathematical properties of geostatistical formulations involving compositional variables. The book 'Geostatistical Analysis of Compositional Data' by Vera Pawlowsky-Glahn and Ricardo Olea (Oxford University Press, 2004), unlike any previous book on geostatistics, directly confronts the mathematical difficulties inherent to applying geostatistics to compositional variables. The book righteously justifies itself with prodigious referencing to previous work addressing nonsensical ranges of estimated values and error, spurious correlation, and singular cross-covariance matrices.

Authors:
Publication Date:
Research Org.:
Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
940856
Report Number(s):
UCRL-JRNL-229488
Journal ID: ISSN 1539-1663; VZJAAB; TRN: US200824%%353
DOE Contract Number:  
W-7405-ENG-48
Resource Type:
Journal Article
Resource Relation:
Journal Name: Vadose Zone Journal, vol. 6, no. 3, August 1, 2007, pp. 684-685; Journal Volume: 6; Journal Issue: 3
Country of Publication:
United States
Language:
English
Subject:
58 GEOSCIENCES; MATRICES; SPATIAL DISTRIBUTION; VECTORS

Citation Formats

Carle, S F. Book Review Geostatistical Analysis of Compositional Data. United States: N. p., 2007. Web.
Carle, S F. Book Review Geostatistical Analysis of Compositional Data. United States.
Carle, S F. Mon . "Book Review Geostatistical Analysis of Compositional Data". United States. doi:. https://www.osti.gov/servlets/purl/940856.
@article{osti_940856,
title = {Book Review Geostatistical Analysis of Compositional Data},
author = {Carle, S F},
abstractNote = {Compositional data are represented as vector variables with individual vector components ranging between zero and a positive maximum value representing a constant sum constraint, usually unity (or 100 percent). The earth sciences are flooded with spatial distributions of compositional data, such as concentrations of major ion constituents in natural waters (e.g. mole, mass, or volume fractions), mineral percentages, ore grades, or proportions of mutually exclusive categories (e.g. a water-oil-rock system). While geostatistical techniques have become popular in earth science applications since the 1970s, very little attention has been paid to the unique mathematical properties of geostatistical formulations involving compositional variables. The book 'Geostatistical Analysis of Compositional Data' by Vera Pawlowsky-Glahn and Ricardo Olea (Oxford University Press, 2004), unlike any previous book on geostatistics, directly confronts the mathematical difficulties inherent to applying geostatistics to compositional variables. The book righteously justifies itself with prodigious referencing to previous work addressing nonsensical ranges of estimated values and error, spurious correlation, and singular cross-covariance matrices.},
doi = {},
journal = {Vadose Zone Journal, vol. 6, no. 3, August 1, 2007, pp. 684-685},
number = 3,
volume = 6,
place = {United States},
year = {Mon Mar 26 00:00:00 EDT 2007},
month = {Mon Mar 26 00:00:00 EDT 2007}
}