Preface

Summary

Sixteen years have elapsed since the appearance of Geological Factor Analysis. The book has been out of print for several years now but it is still frequently cited in the literature. A Russian translation was issued nine years ago. In response to repeated requests from around the world, we have decided to make our work available again, but this time with a wider scope so as to cater for the needs and interests of a greater range of natural scientists.

Although the information presented in the First Edition is far from outmoded, the past few years have witnessed an increasing awareness of several topics of fundamental importance in applied multivariate statistics such as, for example, the stability of eigenvectors, the identification of a typical and influential observations, the analysis of compositional data, the rise of tensor biometry as a valuable tool in evolutionary biology, and canonical correspondence analysis.

In the Preface to the First Edition, we made it quite clear that we used the term factor analysis in the vernacular mode. Despite all caution, however, we were completely misunderstood by one geological reviewer. We therefore repeat most emphatically that “factor analysis” is used here in an informal manner to signify the statistical application of the algebra of eigenvalues and eigenvectors to the analysis of single multivariate samples. To a certain degree, this usage agrees with analyse factorielle des correspondances of the francophone literature.

The rise of the personal computer has brought the possibilities of computing to anybody who so wishes. It is becoming increasingly common to supply a diskette of programs with texts in applied statistics.