Statistical Analysis Of Geological Data

Extensive discussions cover the distribution, sampling, inference, analysis of variances; transformations of univariate statistical methods; analyses of geological trends and multivariate data; ratios and variables of constant sum; exploration for natural resources; and evaluation of computers and geology. No previous knowledge of statistics necessary.

The book presents multivariate statistical methods useful in geological analysis. The essential distinction between multivariate analysis as applied to full-space data (measurements on lengths, heights, breadths etc.) and compositional data is emphasized with particular reference to geochemical data. Each of the methods is accompanied by a practically oriented computer program and backed up by appropriate examples. The computer programs are provided on a compact disk together with trial data-sets and examples of the output. An important feature of this book is the graphical system developed by Dr. Savazzi which is entitled Graph Server. Geological data often deviate from ideal statistical requirements. For this reason, close attention has been paid to the analysis of data that contain atypical observations.

This thoroughly revised edition presents important methods in the quantitative analysis of geologic data. Retains the basic arrangement of the previous edition but expands sections on probability, nonparametric statistics, and Fourier analysis. Contains revised coverage of eigenvalues and eigenvectors, and new coverage of data analysis methods, such as the semivariogram and the process of kriging.

Since Karl Pearson wrote his paper on spurious correlation in 1897, a lot has been said about the statistical analysis of compositional data, mainly by geologists such as Felix Chayes. The solution appeared in the 1980s, when John Aitchison proposed to use Iogratios. Since then, the approach has seen a great expansion, mainly building on the idea of the `natural geometry' of the sample space. Statistics is expected to give sense to our perception of the natural scale of the data, and this is made possible for compositional data using Iogratios. This publication will be a milestone in this process.

Unlike most other sciences, geology does not have a strong tradition of numerical analysis. It is, however, increasingly common for primary geological information to be quantitative rather than descriptive, and analysis of numerical data is now a skill of immense value to any earth scientist. The authors of this book have set out to provide students at undergraduate and graduate level with a thorough grounding in the statistical techniques required in the earth sciences. All the modern statistical methods employed by geologists and geophysicists are covered, with clear worked examples using the type of data the reader is likely to encounter.