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.
For earth scientists, earth-science libraries and research workers concerned with quantitative geosciences.
Chapter headings: Preface. Introduction. Graph Server and Graph Wizard. Methods for Analysing a Sample Drawn From a Single Population. Comparing Samples From Two Populations: The Discriminant Function. Analysis of Several Groups: Canonical Variate Analysis. Correlating Between Sets. Some Problems in Petrology and Geochemistry. Miscellaneous Examples. Glossary of Program Operations. References. Contents of Accompanying Compact Disk.
- No. of pages:
- © Elsevier Science 1999
- 24th November 1999
- Elsevier Science
- eBook ISBN:
- Hardcover ISBN:
Department of Historical Geology and Palaeontology, Institute of Earth Sciences, University of Uppsala, Uppsala 75236, Sweden
Department of Historical Geology and Palaeontology, University of Uppsala, Sweden
@from:(A.F. Militino, Universidad Pùblica de Navarra, Spain) @qu:This book contributes to a better understanding of multivariate statistical analysis in the earth sciences.(...)this monograph is a good support and a textbook addressed to students, researchers, instructors and general practitioners of multivariate statistical techniques in the geosciences and it is highly recommended. @source:Statistical Software Newsletter, Vol. 34, No. 4