Nonparametrics: Statistical Methods Based on Ranks

I agree with the other reviewer that this text is a classical by Erich Lehmann. It is great that this book which has been out of print for many years is back in print with a new publisher. There is a lot of wisdom conveyed in this book along with very useful nonparametric methods that stand the test of time. I cannot comment on the publication quality of the reprinted edition as I still have (in excellent condition) my copy of the original 1975 publication that was published by Holden-Day. Lehmann always writes eloquently and his treatment is always authoritative and accurate. However, most of his texts are advanced theoretical books for graduate students in statistics. This one is very different. As he says in his preface, "The purpose of this book is to provide an introduction to nonparametric methods for the analysis and planning of comparative studies." As such he has written it for practitioners. It is filled with illustrative examples of the techniques and intuitive descriptions. There is some mathematics and many exercises at the end of the chapters, but it is intended as a reference text as well as a text for an introductory course. He is very successful in this endeavor. I have found it very useful over the years and still use it as a reference. In fact, I am sometimes asked as a consultant what procedures are available to test for trends in data. When a nonparametric approach appears warranted, I often refer them to Chapter 7 in this book. It gives a wonderful treatment of tests for independence and provides insight into the tests that are powerful against the alternative hypothesis of a trend over time.