It is now over 35 years since the first edition of Cluster Analysis was published. During this lengthy time period the topic has been in, and occasionally out, of fashion, but the book itself has remained a popular and hopefully useful account of a wide range of numerical methods for exploring multivariate data with a view to uncovering or discovering groups or clusters of homogeneous observations. Such clustering techniques have been employed in a remarkable number of different disciplines. In psychiatry the techniques have been used to refine existing diagnostic categories. In archaeology clustering has been used to investigate the relationship between various types of artefacts. In market research, methods of cluster analysis have been applied to produce groups of consumers with different purchasing patterns. And in the first decade of the 21st century cluster analysis is of considerable interest and importance in the new field of bioinformatics, where it has been used to identify groups of genes with similar patterns of expression with the aim of helping to answer questions of how gene expression is affected by various diseases and which genes are responsible for specific hereditary diseases.