I like this little old book. It gives a simple introduction to characteristic based classification methods. The book is very readable and the math presented is fairly easy to understand. The chapters cover the following:
[1] Introduction
[2] Taxonomic characters
[3] Measures of similarity
[4] Principal components analysis
[5] Multidimensional scaling
[6] Cluster analysis
[7] Identification and assignment techniques
[8] Constructing evolutionary trees
One caveat, because the copyright is old (1982) many more recently developed methods [such as neighbor-joining, maximum likelihood, and Bayesian methods] are not mentioned while others [parsimony] are only mention casually. However the treatment of classic distance clustering methods is fairly good.